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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utt
    -0.07
     bald
    -0.07
     کوت
    -0.07
     darf
    -0.07
     конт
    -0.07
    owards
    -0.06
    war
    -0.06
    *>
    -0.06
    ованих
    -0.06
     cata
    -0.06
    POSITIVE LOGITS
    fun
    0.06
    分析
    0.06
     bidder
    0.06
     bölge
    0.06
    .translatesAutoresizingMaskIntoConstraints
    0.06
     CLIIIK
    0.06
     PageInfo
    0.06
    binding
    0.06
    .strategy
    0.06
    (freq
    0.06
    Act Density 0.000%

    No Known Activations