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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $L
    -0.07
    .",↵
    -0.07
    ags
    -0.06
    ）↵
    -0.06
    (unittest
    -0.06
     Hv
    -0.06
    �
    -0.06
     Duck
    -0.06
    Available
    -0.06
    _notifications
    -0.06
    POSITIVE LOGITS
    Abr
    0.07
    055
    0.06
    vely
    0.06
    نع
    0.06
    馆
    0.06
     Krist
    0.06
    wil
    0.06
    050
    0.06
    бі
    0.06
    travel
    0.06
    Act Density 0.048%

    No Known Activations