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

    Neuronpedia

    INDEX
    Explanations

    pain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    逃
    -0.07
    Sand
    -0.06
     reputation
    -0.06
     warmth
    -0.06
     fj
    -0.06
    混
    -0.06
    _ASSUME
    -0.06
    ====
    -0.06
     demonstrating
    -0.06
     temperament
    -0.06
    POSITIVE LOGITS
     Innovative
    0.07
    _SEQUENCE
    0.07
    inspace
    0.07
    oge
    0.06
    UIStoryboardSegue
    0.06
    FFF
    0.06
    letal
    0.06
    اني
    0.06
     sidelined
    0.06
    StringValue
    0.06
    Act Density 0.047%

    No Known Activations