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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucson
    -0.07
    iffany
    -0.07
    Notify
    -0.06
     challenger
    -0.06
    pro
    -0.06
     incorporation
    -0.06
    イド
    -0.06
    .renderer
    -0.06
     Impro
    -0.06
     Hacker
    -0.06
    POSITIVE LOGITS
    <Path
    0.08
     "***
    0.07
    (tf
    0.07
     */
↵
↵
    0.07
    <dd
    0.07
    "profile
    0.06
     mechanism
    0.06
     cafe
    0.06
    "default
    0.06
    الأ
    0.06
    Act Density 0.001%

    No Known Activations