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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    斫
    -0.07
    �
    -0.07
    bigint
    -0.07
     Projekt
    -0.07
    float
    -0.07
    _DSP
    -0.07
     pagan
    -0.07
    爚
    -0.07
    aceutical
    -0.07
    ชวน
    -0.07
    POSITIVE LOGITS
    ometimes
    0.08
    (dim
    0.07
    .Av
    0.07
    יני
    0.07
     hormonal
    0.07
    Sun
    0.07
    _price
    0.06
    巡逻
    0.06
    下行
    0.06
    esterday
    0.06
    Act Density 0.091%

    No Known Activations