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

    Neuronpedia

    INDEX
    Explanations

    axis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reversed
    -0.07
    ;padding
    -0.07
    _via
    -0.07
     uv
    -0.06
     persuade
    -0.06
     harbour
    -0.06
     mates
    -0.06
     cautious
    -0.06
     completion
    -0.06
     Typeface
    -0.06
    POSITIVE LOGITS
    イド
    0.06
    Dire
    0.06
    érica
    0.06
    rang
    0.06
    'nda
    0.06
    voř
    0.06
    696
    0.06
    693
    0.06
     гор
    0.06
    ottle
    0.06
    Act Density 0.243%

    No Known Activations