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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有时候
    0.68
     sağlar
    0.68
     গত
    0.64
     이번
    0.58
    每次
    0.58
    번호
    0.58
     заранее
    0.58
    Якщо
    0.58
     rendimiento
    0.57
     கடந்த
    0.57
    POSITIVE LOGITS
     onwards
    1.34
     onward
    1.18
     silam
    1.16
    년
    0.96
     সালের
    0.93
    ′
    0.93
    ish
    0.88
     թվական
    0.84
     biennium
    0.84
    ″
    0.84
    Act Density 0.172%

    No Known Activations