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

    Neuronpedia

    INDEX
    Explanations

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _accel
    -0.07
    $j
    -0.06
    .scheme
    -0.06
     Exit
    -0.06
    存在
    -0.06
    .yellow
    -0.06
    /base
    -0.06
     yanlış
    -0.06
     huy
    -0.06
    .references
    -0.06
    POSITIVE LOGITS
    ornment
    0.07
    bib
    0.06
    raft
    0.06
     grad
    0.06
     panor
    0.06
    oplay
    0.06
    措施
    0.06
    (Current
    0.06
    �
    0.06
    фици
    0.06
    Act Density 0.011%

    No Known Activations