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

    Neuronpedia

    INDEX
    Explanations

    start of html document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wget
    2.15
    用語
    2.06
    Боль
    2.05
    ible
    1.99
    νες
    1.99
    GameObject
    1.98
     digamos
    1.96
    <0x80>
    1.96
    RE
    1.95
    ரே
    1.93
    POSITIVE LOGITS
    tted
    2.09
    jší
    2.03
    ̾
    2.02
     adequada
    1.98
    transferases
    1.96
     dignitaries
    1.87
    これも
    1.87
     VGM
    1.84
    то
    1.82
     лишь
    1.82
    Act Density 0.003%

    No Known Activations