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

    Neuronpedia

    INDEX
    Explanations

    phenotype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dark
    -0.07
     module
    -0.07
    okud
    -0.07
    .touches
    -0.06
     Parts
    -0.06
    avs
    -0.06
    ически
    -0.06
    ва
    -0.06
     привод
    -0.06
    _players
    -0.06
    POSITIVE LOGITS
    ){
↵
    0.07
     Safety
    0.06
    Safety
    0.06
    ],"
    0.06
     Benny
    0.06
    ihilation
    0.06
    bilir
    0.06
    afety
    0.06
     �
    0.06
     ServletException
    0.06
    Act Density 0.013%

    No Known Activations