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

    Neuronpedia

    INDEX
    Explanations

    computer system signals and their related code structures

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

    Code snippets or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aqu
    -0.54
     well
    -0.52
     يتيمه
    -0.48
     Aqu
    -0.47
    GrantedAuthority
    -0.47
    …………
    -0.46
     far
    -0.45
     stop
    -0.45
    aran
    -0.44
     mal
    -0.43
    POSITIVE LOGITS
    GraphicsUnit
    0.75
     '\\;'
    0.67
     GetEnumerator
    0.64
     ainfi
    0.61
     appuntamento
    0.61
    bbene
    0.59
    RunAsync
    0.59
     avoient
    0.58
    moiselle
    0.58
    قایناق‌لار
    0.57
    Act Density 0.298%

    No Known Activations