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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bias
    -0.08
    _edge
    -0.07
     hashed
    -0.07
    limits
    -0.07
     tầng
    -0.07
    $errors
    -0.07
    仔
    -0.06
     prestige
    -0.06
    .access
    -0.06
     fen
    -0.06
    POSITIVE LOGITS
    すると
    0.07
     благодаря
    0.06
     Consequently
    0.06
    oruč
    0.06
    agation
    0.06
     designate
    0.06
     However
    0.06
    _INVALID
    0.06
     Using
    0.06
    รง
    0.06
    Act Density 0.000%

    No Known Activations