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

    Neuronpedia

    INDEX
    Explanations

    say "display"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Temp
    -0.07
     Drinking
    -0.06
     plea
    -0.06
    觌
    -0.06
    _threshold
    -0.06
     wanna
    -0.06
    负责任
    -0.06
    AGAIN
    -0.06
    得了
    -0.06
     Leading
    -0.06
    POSITIVE LOGITS
    //================================================================
    0.07
    笼
    0.07
     microbi
    0.07
    atten
    0.07
    保养
    0.07
    Calculate
    0.07
    c
    0.07
     expansive
    0.07
    当地政府
    0.07
    dated
    0.07
    Act Density 0.004%

    No Known Activations