Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structured formats or data representations, such as arrays or matrices, in mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or equations in LaTeX format

    np_acts-logits-general · gemini-2.0-flash

    chemical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.93
    expandindo
    -0.88
     GenerationType
    -0.78
    WriteBarrier
    -0.76
     AssemblyTitle
    -0.74
    CrossRef
    -0.70
    ⓧ
    -0.67
    synthesize
    -0.66
     AssemblyCulture
    -0.65
     snippetHide
    -0.65
    POSITIVE LOGITS
     Dandy
    0.52
    iotto
    0.51
     argint
    0.49
     retr
    0.47
    bcc
    0.46
    Initialization
    0.46
     رف
    0.45
    coccal
    0.43
     gerais
    0.43
    raa
    0.43
    Act Density 0.116%

    No Known Activations