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

    Neuronpedia

    INDEX
    Explanations

    code, structured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictatorship
    -0.08
     qi
    -0.07
    쪽
    -0.07
    Milliseconds
    -0.06
    .getRequest
    -0.06
    المعروف
    -0.06
    .contentType
    -0.06
    _ele
    -0.06
    𝘌
    -0.06
    绂
    -0.06
    POSITIVE LOGITS
    CAL
    0.07
     restless
    0.07
    ły
    0.07
    sdale
    0.07
    逃离
    0.07
     BG
    0.07
    angers
    0.07
     IMP
    0.07
     rocked
    0.06
     symptoms
    0.06
    Act Density 0.018%

    No Known Activations