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

    Neuronpedia

    INDEX
    Explanations

    shame and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    コメント
    0.52
    實際上
    0.51
     irony
    0.48
    行程
    0.47
     commented
    0.46
     букме
    0.45
    曛
    0.45
    蕖
    0.45
    4
    0.44
    ゲーム
    0.44
    POSITIVE LOGITS
    eis
    0.44
    FBSDKAppEvents
    0.44
    ısından
    0.43
    攸
    0.42
    ól
    0.41
     frontiers
    0.41
    sız
    0.40
    opausal
    0.40
     ;(
    0.40
    риш
    0.40
    Act Density 0.002%

    No Known Activations