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

    Neuronpedia

    INDEX
    Explanations

    ignite your fire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getKeyCode
    0.44
     wars
    0.40
     banal
    0.38
    Wars
    0.38
     مطال
    0.37
     muslin
    0.37
    坫
    0.37
    砳
    0.36
     గ్రహ
    0.36
    FormField
    0.35
    POSITIVE LOGITS
    PW
    0.41
     natives
    0.38
    Outgoing
    0.38
    х
    0.38
    дно
    0.38
     amplitudes
    0.37
    μένα
    0.36
    px
    0.36
    pir
    0.36
    やかに
    0.36
    Act Density 0.000%

    No Known Activations