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

    Neuronpedia

    INDEX
    Explanations

    pond

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INATION
    -0.07
    æ
    -0.07
     daycare
    -0.07
     accompany
    -0.07
    mr
    -0.07
    鸩
    -0.07
     Default
    -0.06
    vanced
    -0.06
    ًا
    -0.06
    atomy
    -0.06
    POSITIVE LOGITS
     Exped
    0.07
    +$
    0.07
    𝘗
    0.07
     един
    0.07
     entrepreneurs
    0.07
    	↵	↵	↵	↵
    0.06
    钲
    0.06
    骁
    0.06
    categories
    0.06
    낟
    0.06
    Act Density 0.002%

    No Known Activations