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

    Neuronpedia

    INDEX
    Explanations

    enabled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fine
    -0.08
    勾
    -0.08
     bur
    -0.07
    unsubscribe
    -0.07
     Swim
    -0.07
    𫠊
    -0.07
    .fac
    -0.07
    bone
    -0.06
    _timeline
    -0.06
     dog
    -0.06
    POSITIVE LOGITS
     MMP
    0.07
    ⵕ
    0.07
    คำถาม
    0.07
    مسأل
    0.07
     şart
    0.07
    $args
    0.06
    🗨
    0.06
     tatsäch
    0.06
    ﺟ
    0.06
    Gradient
    0.06
    Act Density 0.021%

    No Known Activations