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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Measurement
    -0.08
    gs
    -0.07
     Calculate
    -0.06
    平
    -0.06
    Submission
    -0.06
    aud
    -0.06
    -copy
    -0.06
     Lies
    -0.06
    505
    -0.06
     축
    -0.06
    POSITIVE LOGITS
     J
    0.07
    _phrase
    0.06
     subtle
    0.06
     피해
    0.06
    ่ท
    0.06
    	logger
    0.06
    ReLU
    0.06
    rubu
    0.06
     inst
    0.06
    ehen
    0.06
    Act Density 0.001%

    No Known Activations