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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pluto
    -0.07
     Garrett
    -0.07
    sock
    -0.07
    亓
    -0.07
    🏩
    -0.07
     현재
    -0.07
     mét
    -0.07
     прид
    -0.07
    packed
    -0.07
    盱
    -0.07
    POSITIVE LOGITS
    enumerate
    0.07
    _rnn
    0.06
    ulative
    0.06
    _MATRIX
    0.06
    iameter
    0.06
    _baseline
    0.06
     gì
    0.06
    已经有了
    0.06
    ですから
    0.06
    炷
    0.06
    Act Density 0.009%

    No Known Activations