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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Container
    -0.08
    更重要的
    -0.07
    趕
    -0.07
    енно
    -0.07
    打工
    -0.07
     Joseph
    -0.07
     desperately
    -0.07
     beside
    -0.07
     eventually
    -0.06
    치
    -0.06
    POSITIVE LOGITS
    -tone
    0.08
     /*<<<
    0.07
    -rest
    0.07
    -adjust
    0.07
     abst
    0.07
    _AUD
    0.07
    KY
    0.07
     paperback
    0.07
    /--
    0.06
    −
    0.06
    Act Density 0.000%

    No Known Activations