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

    Neuronpedia

    INDEX
    Explanations

    saving files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erectile
    -0.07
    inject
    -0.07
    ':↵↵
    -0.07
     Inject
    -0.07
     Processing
    -0.07
    ിപ്പ
    -0.07
     मेर
    -0.07
     purified
    -0.07
     trains
    -0.07
     aigu
    -0.07
    POSITIVE LOGITS
     გადაი
    0.09
     çək
    0.09
     welches
    0.09
    /save
    0.08
     lần
    0.08
    首次
    0.08
    .save
    0.08
     bezeichnet
    0.08
    .Save
    0.08
     بعنوان
    0.08
    Act Density 0.002%

    No Known Activations