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

    Neuronpedia

    INDEX
    Explanations

    evolutionary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empres
    -0.07
     articulated
    -0.07
    .Lo
    -0.07
     nợ
    -0.06
     subdued
    -0.06
     Gerr
    -0.06
     목소
    -0.06
    abetic
    -0.06
    _routing
    -0.06
    很多
    -0.06
    POSITIVE LOGITS
     Evolution
    0.10
     evolution
    0.09
    ATOM
    0.08
     evolutionary
    0.08
     vývoj
    0.07
     طول
    0.07
     Ev
    0.07
     starttime
    0.07
     arrayWith
    0.07
    Turkey
    0.07
    Act Density 0.008%

    No Known Activations