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

    Neuronpedia

    INDEX
    Explanations

    business/professional contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Used
    -0.07
     suicides
    -0.07
    Let
    -0.06
    dense
    -0.06
    affle
    -0.06
    -resistant
    -0.06
    <IEnumerable
    -0.06
    ün
    -0.06
    eki
    -0.06
    StartElement
    -0.06
    POSITIVE LOGITS
     pregn
    0.07
     collaps
    0.06
     facto
    0.06
     deser
    0.06
     MLP
    0.06
     Hobby
    0.06
     отд
    0.06
    swing
    0.06
    >>()
    0.06
     पड़
    0.06
    Act Density 0.065%

    No Known Activations