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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bw
    -0.06
    验证
    -0.06
    warning
    -0.06
     لي
    -0.06
     massac
    -0.06
     Sauce
    -0.06
     Slut
    -0.06
    假
    -0.06
    logged
    -0.06
    ož
    -0.06
    POSITIVE LOGITS
     objectMapper
    0.07
    andbox
    0.07
     imply
    0.06
    ErrorCode
    0.06
     claiming
    0.06
     IsPlainOldData
    0.06
    .toJSON
    0.06
    .addAll
    0.06
     claims
    0.06
    している
    0.06
    Act Density 0.013%

    No Known Activations