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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adolescent
    -0.07
     looming
    -0.07
    紀
    -0.06
     dispos
    -0.06
     legalization
    -0.06
     Abstract
    -0.06
     migraine
    -0.06
    φυ
    -0.06
    بار
    -0.06
     dio
    -0.06
    POSITIVE LOGITS
     Uber
    0.07
    ★
    0.07
    slice
    0.06
     erw
    0.06
    âte
    0.06
    _remove
    0.06
    ("/:
    0.06
    기의
    0.06
    Ul
    0.06
    {"
    0.06
    Act Density 0.000%

    No Known Activations