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

    Neuronpedia

    INDEX
    Explanations

    tab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Henri
    -0.06
    <IEnumerable
    -0.06
    beck
    -0.06
    etric
    -0.06
    腐
    -0.06
     ч
    -0.06
    нике
    -0.06
     board
    -0.06
    -blocking
    -0.06
     amongst
    -0.06
    POSITIVE LOGITS
     доктор
    0.08
    /{$
    0.06
    ')){↵
    0.06
     Contacts
    0.06
    _warnings
    0.06
    Pwd
    0.06
    \Module
    0.06
    requently
    0.06
    .Accessible
    0.06
    兰
    0.06
    Act Density 0.022%

    No Known Activations