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

    Neuronpedia

    INDEX
    Explanations

    fictional worlds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -wise
    -0.08
    =self
    -0.08
     мил
    -0.07
     Gemini
    -0.07
     Hath
    -0.07
     ansible
    -0.07
    Combo
    -0.07
     deze
    -0.07
     RV
    -0.07
    _LONG
    -0.07
    POSITIVE LOGITS
    泪水
    0.07
    眈
    0.07
    مياه
    0.06
    charted
    0.06
    ража
    0.06
     bullets
    0.06
     применения
    0.06
    מרק
    0.06
     tarde
    0.06
    胣
    0.06
    Act Density 0.054%

    No Known Activations