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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xlabel
    -0.07
     ballot
    -0.07
     peel
    -0.06
     busiest
    -0.06
    罗
    -0.06
     Julio
    -0.06
     otur
    -0.06
    استان
    -0.06
    {},
    -0.06
    СТ
    -0.06
    POSITIVE LOGITS
    .ge
    0.07
    _n
    0.07
    mark
    0.07
     geschichten
    0.06
     professions
    0.06
    _checkpoint
    0.06
     Pap
    0.06
     lightly
    0.06
     Vic
    0.06
    amation
    0.06
    Act Density 0.009%

    No Known Activations