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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strict
    -0.07
     burning
    -0.07
    �
    -0.07
     se
    -0.07
    ATS
    -0.07
    Trade
    -0.06
    ORLD
    -0.06
    ittance
    -0.06
     hooks
    -0.06
    zed
    -0.06
    POSITIVE LOGITS
    션
    0.06
     Swan
    0.06
     cultivation
    0.06
    edis
    0.06
    Vintage
    0.06
     Vintage
    0.06
    TokenType
    0.06
    .providers
    0.06
     unitOfWork
    0.06
    .substr
    0.06
    Act Density 0.000%

    No Known Activations