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

    Neuronpedia

    INDEX
    Explanations

    Programming requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dexter
    -0.07
     dbl
    -0.07
     steroids
    -0.07
    Without
    -0.07
     vaccines
    -0.06
    .jdbc
    -0.06
    uden
    -0.06
    结构性
    -0.06
    ѻ
    -0.06
    /db
    -0.06
    POSITIVE LOGITS
    聽
    0.07
    \">
    0.07
    char
    0.07
     violation
    0.07
    킹
    0.07
     absorbing
    0.07
    戛
    0.07
    eated
    0.07
    _scalar
    0.07
    _CARD
    0.07
    Act Density 0.056%

    No Known Activations