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

    Neuronpedia

    INDEX
    Explanations

    spread out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �权
    -0.07
    런
    -0.07
    рус
    -0.06
     ברחבי
    -0.06
    不满意
    -0.06
    argin
    -0.06
    Camp
    -0.06
     rnn
    -0.06
    vertis
    -0.06
     activate
    -0.06
    POSITIVE LOGITS
    乾
    0.07
    .Children
    0.07
    捏
    0.07
    _emails
    0.07
    .getEnd
    0.07
     cryptocurrencies
    0.07
    .children
    0.07
    滴滴
    0.07
     investigación
    0.06
    .qt
    0.06
    Act Density 0.024%

    No Known Activations