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

    Neuronpedia

    INDEX
    Explanations

    altitude, gravity, velocity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ただし
    1.04
     mín
    0.99
     defective
    0.96
     gesprochen
    0.95
    yoruz
    0.94
    液晶
    0.93
     대신
    0.90
    割合
    0.90
     Förderung
    0.90
    哚
    0.89
    POSITIVE LOGITS
    𝗺
    1.08
    suppliers
    1.07
     депутат
    1.03
    tram
    1.00
    publishing
    0.97
    comics
    0.95
    তম
    0.94
    tender
    0.93
     trabajar
    0.93
    𝙠
    0.92
    Act Density 0.000%

    No Known Activations