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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اين
    -0.08
    Yang
    -0.08
    ten
    -0.07
     dicks
    -0.07
    eel
    -0.07
     Samuel
    -0.07
    vip
    -0.06
     denen
    -0.06
    252
    -0.06
    teenth
    -0.06
    POSITIVE LOGITS
    (for
    0.09
     For
    0.09
    For
    0.09
    FOR
    0.09
    OR
    0.09
    _FOR
    0.09
    or
    0.09
     Фор
    0.08
    .For
    0.08
     IF
    0.08
    Act Density 0.060%

    No Known Activations