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

    Neuronpedia

    INDEX
    Explanations

    conversion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.93
    <bos>
    -0.80
    FormTagHelper
    -0.66
    ropractic
    -0.64
     незавершена
    -0.63
     للاسماء
    -0.61
    Ӕ
    -0.60
     للمعارف
    -0.59
     correndo
    -0.59
    closedir
    -0.59
    POSITIVE LOGITS
     to
    0.56
    r
    0.54
    ary
    0.53
    CrossRef
    0.53
    k
    0.52
    ar
    0.52
    i
    0.51
    ian
    0.50
    b
    0.49
    to
    0.49
    Act Density 0.906%

    No Known Activations