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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and variable declarations

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

    algebraic geometry mathematical notions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.63
    PreferredItem
    -0.52
     mijne
    -0.51
    MessageOf
    -0.49
     Италијани
    -0.48
    Portály
    -0.48
     typelib
    -0.48
    dcmtk
    -0.47
     iVar
    -0.47
     jspb
    -0.46
    POSITIVE LOGITS
     char
    0.43
     quedando
    0.42
    JAKARTA
    0.42
     marked
    0.39
     extended
    0.38
     characterised
    0.38
     modified
    0.36
     karş
    0.36
     adapted
    0.35
     quedó
    0.35
    Act Density 0.076%

    No Known Activations