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

    Neuronpedia

    INDEX
    Explanations

    formatting/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cm
    -0.07
    .↵↵↵↵
    -0.06
     Instructions
    -0.06
    checkBox
    -0.06
     qb
    -0.06
     class
    -0.06
     από
    -0.06
     noisy
    -0.06
     Cos
    -0.06
     onChangeText
    -0.06
    POSITIVE LOGITS
    urdu
    0.07
    (Layout
    0.07
    .Mongo
    0.06
    unicorn
    0.06
    股
    0.06
     тур
    0.06
    Quant
    0.06
    меж
    0.06
    _TUN
    0.06
    834
    0.06
    Act Density 0.011%

    No Known Activations