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

    Neuronpedia

    INDEX
    Explanations

    harmful situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    娣
    -0.07
    dzi
    -0.07
    Kİ
    -0.07
    dre
    -0.07
     Biom
    -0.07
    ('(
    -0.07
    Jur
    -0.07
     pä
    -0.07
    aygı
    -0.07
    enter
    -0.06
    POSITIVE LOGITS
    简洁
    0.07
    活动现场
    0.07
     UIFont
    0.07
    projectId
    0.07
     herramient
    0.07
    的速度
    0.06
    �
    0.06
     ineffective
    0.06
    ']){↵
    0.06
    зон
    0.06
    Act Density 0.037%

    No Known Activations