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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tabs
    -0.07
    _TRIGGER
    -0.06
    จำหน
    -0.06
    وان
    -0.06
     اث
    -0.06
    THOOK
    -0.06
     ημέ
    -0.06
    USTER
    -0.06
    ฮ
    -0.06
    لوب
    -0.06
    POSITIVE LOGITS
    кая
    0.07
     recovered
    0.07
    conditional
    0.06
     Clothes
    0.06
    crop
    0.06
     těla
    0.06
     Statistical
    0.06
     modelling
    0.06
     INTERFACE
    0.06
     collar
    0.06
    Act Density 0.000%

    No Known Activations