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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /net
    -0.07
    _SO
    -0.06
    .LE
    -0.06
    ドラ
    -0.06
    Ill
    -0.06
    sig
    -0.06
    lığının
    -0.06
     Льв
    -0.06
    coe
    -0.06
     bracelets
    -0.06
    POSITIVE LOGITS
    (optarg
    0.06
    super
    0.06
    chai
    0.06
    <footer
    0.05
     warned
    0.05
    Fullscreen
    0.05
    reator
    0.05
    機能
    0.05
     баб
    0.05
    __$
    0.05
    Act Density 0.191%

    No Known Activations