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

    Neuronpedia

    INDEX
    Explanations

    LIN

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Operator
    -0.07
     proposed
    -0.07
     capacity
    -0.07
     Utilities
    -0.07
    _contrib
    -0.07
     facilities
    -0.07
     vibrations
    -0.06
     waves
    -0.06
    _predict
    -0.06
     Pediatric
    -0.06
    POSITIVE LOGITS
    rei
    0.08
     naï
    0.07
     сок
    0.07
     rall
    0.06
    .dex
    0.06
    取得
    0.06
    $out
    0.06
    Intel
    0.06
    (touch
    0.06
     Axel
    0.06
    Act Density 0.002%

    No Known Activations