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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $r
    -0.06
    iddles
    -0.06
    -temp
    -0.06
    级
    -0.06
     plo
    -0.06
    Files
    -0.06
     ダ
    -0.06
    드로
    -0.06
    Generator
    -0.06
     Pending
    -0.06
    POSITIVE LOGITS
     "=
    0.07
    (","
    0.07
    _tv
    0.06
     +#+#+#+
    0.06
    184
    0.06
     minX
    0.06
    (tv
    0.06
     bury
    0.06
    essenger
    0.06
     latin
    0.06
    Act Density 0.033%

    No Known Activations