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

    Neuronpedia

    INDEX
    Explanations

    EXISTS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .putString
    -0.07
    .....↵↵
    -0.07
    .XtraBars
    -0.06
     Liberty
    -0.06
    (note
    -0.06
    ighb
    -0.06
     Jared
    -0.06
    adle
    -0.06
     Troy
    -0.06
     grabbed
    -0.06
    POSITIVE LOGITS
    exists
    0.07
    -pos
    0.06
     adidas
    0.06
    cq
    0.06
    (INVOKE
    0.06
     sausage
    0.06
    ヴィ
    0.06
     https
    0.05
    $val
    0.05
     forControlEvents
    0.05
    Act Density 0.001%

    No Known Activations