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

    Neuronpedia

    INDEX
    Explanations

    arrive on, this month

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    -1.00
     position
    -0.94
     all
    -0.93
    ȼ
    -0.92
    ּוֹ
    -0.90
    地理
    -0.89
    O
    -0.88
    ✨
    -0.88
    </em>
    -0.88
     glyphicon
    -0.88
    POSITIVE LOGITS
    哈哈哈哈
    1.31
     diário
    1.25
    気がします
    1.22
     règne
    1.16
     fornece
    1.16
    誒
    1.15
     exitoso
    1.13
    Veuillez
    1.13
    ➴
    1.12
    獼
    1.12
    Act Density 0.077%

    No Known Activations