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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ZX
    -0.07
     cornerstone
    -0.07
    属性
    -0.07
    دي
    -0.06
     blackjack
    -0.06
    -Control
    -0.06
    Folder
    -0.06
     geometric
    -0.06
    溇
    -0.06
    арь
    -0.06
    POSITIVE LOGITS
     Milf
    0.07
     compliments
    0.07
    lahoma
    0.07
    _approved
    0.07
    เกาหล
    0.06
     metav
    0.06
    captcha
    0.06
    (pass
    0.06
    ENOMEM
    0.06
    넢
    0.06
    Act Density 0.000%

    No Known Activations