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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tikang
    -0.99
     autorytatywna
    -0.85
    NUMX
    -0.84
     Bourgoin
    -0.83
    principalColumn
    -0.82
     (-)
    -0.81
    rungsseite
    -0.81
     propOrder
    -0.80
    $($
    -0.78
    存于互联网档案馆
    -0.78
    POSITIVE LOGITS
    body
    0.46
    ↵
    0.40
    :
    0.35
    bow
    0.35
     lois
    0.33
    ?
    0.33
    —
    0.33
    bot
    0.33
    bodies
    0.32
    fa
    0.32
    Act Density 0.005%

    No Known Activations