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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NewItem
    -0.07
    PLIT
    -0.06
     Engagement
    -0.06
    pton
    -0.06
     patrol
    -0.06
    タル
    -0.06
    gorith
    -0.06
    好き
    -0.06
     Nikki
    -0.06
    Either
    -0.06
    POSITIVE LOGITS
     finns
    0.07
    _consumer
    0.07
    printw
    0.06
    oky
    0.06
     ا
    0.06
    makta
    0.06
    eme
    0.06
    ящ
    0.06
    _DIV
    0.06
    _Options
    0.06
    Act Density 0.001%

    No Known Activations