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

    Neuronpedia

    INDEX
    Explanations

    pivot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tour
    -0.09
    reffen
    -0.08
     barrage
    -0.07
     overrun
    -0.07
    	Send
    -0.07
    3
    -0.07
    ,:),
    -0.07
     imprisoned
    -0.07
    罅
    -0.07
    Mark
    -0.07
    POSITIVE LOGITS
     pivot
    0.08
    埵
    0.07
     POS
    0.07
    ité
    0.07
    QUESTION
    0.07
    水平
    0.06
    咪
    0.06
     כאמ
    0.06
    ﾋ
    0.06
    ------↵
    0.06
    Act Density 0.004%

    No Known Activations