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

    Neuronpedia

    INDEX
    Explanations

    explaining with examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기반
    0.35
    𝑡
    0.33
    า
    0.32
    них
    0.31
    ンダー
    0.31
     व
    0.30
    υ
    0.30
     fichiers
    0.29
    ぞれ
    0.29
     모델
    0.29
    POSITIVE LOGITS
    H
    0.45
    S
    0.41
    F
    0.37
    W
    0.36
    Z
    0.34
    quele
    0.34
    J
    0.34
    E
    0.33
    D
    0.32
    K
    0.32
    Act Density 0.000%

    No Known Activations