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

    Neuronpedia

    INDEX
    Explanations

    published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esp
    -0.07
    兴奋
    -0.07
    map
    -0.07
    pre
    -0.07
    �
    -0.07
    train
    -0.07
     agg
    -0.07
     prec
    -0.07
    thalm
    -0.06
     esp
    -0.06
    POSITIVE LOGITS
    넜
    0.07
    _callable
    0.07
     שאנ
    0.07
     הגיע
    0.07
    \Customer
    0.07
    _aliases
    0.06
    䠀
    0.06
     closes
    0.06
    防晒
    0.06
     Lowe
    0.06
    Act Density 0.015%

    No Known Activations