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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gar
    -0.07
     shar
    -0.06
     Jeg
    -0.06
    腦
    -0.06
    -cart
    -0.06
     hatte
    -0.06
    单
    -0.06
    /rem
    -0.06
     Pedro
    -0.06
     lö
    -0.06
    POSITIVE LOGITS
     (!((
    0.06
     INDIRECT
    0.06
    (before
    0.06
    .Op
    0.06
    NSMutableDictionary
    0.06
    \Cache
    0.06
    ше
    0.06
     อ
    0.06
     apopt
    0.06
     wanting
    0.06
    Act Density 0.282%

    No Known Activations