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

    Neuronpedia

    INDEX
    Explanations

    James P

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused871>
    0.81
     вікісторінку
    0.81
    <unused1634>
    0.81
    <unused58>
    0.77
    𒋩
    0.77
    <unused784>
    0.77
    𒌆
    0.77
     শুক্রাচার্য
    0.77
    nilvadipine
    0.76
    <unused839>
    0.76
    POSITIVE LOGITS
    I
    1.21
    J
    1.14
    M
    1.10
    A
    1.06
    H
    1.03
    W
    1.02
    P
    1.01
    S
    1.00
    E
    0.99
    T
    0.98
    Act Density 0.282%

    No Known Activations