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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation `\mathcal{`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ログイン
    0.39
     বাতাস
    0.38
    接口
    0.37
     timpul
    0.37
    ,":
    0.37
     sessionId
    0.37
     andRow
    0.37
     conclusione
    0.37
     mucha
    0.36
     consolidation
    0.36
    POSITIVE LOGITS
     M
    0.52
     S
    0.51
     Z
    0.49
     L
    0.48
     Q
    0.45
    S
    0.45
     C
    0.45
     V
    0.45
     B
    0.45
     G
    0.45
    Act Density 0.004%

    No Known Activations