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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    are
    -0.55
    -
    -0.51
    '
    -0.50
    It
    -0.50
    ‘
    -0.48
    This
    -0.47
    ’
    -0.47
    There
    -0.46
    (
    -0.46
    In
    -0.45
    POSITIVE LOGITS
     snippetHide
    1.25
    expandindo
    1.20
     Савезне
    1.05
     للمعارف
    1.05
    ftagPool
    1.02
    تقاوى
    1.00
     defaultstate
    1.00
    IsMutable
    0.98
     Administrativna
    0.96
     myſelf
    0.96
    Act Density 0.209%

    No Known Activations