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

    Neuronpedia

    INDEX
    Explanations

    Explorer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _km
    -0.07
    '];?>
    -0.06
     racism
    -0.06
     d
    -0.06
    cal
    -0.06
     plaisir
    -0.06
    .ak
    -0.06
    ercise
    -0.06
     Celebr
    -0.06
     ===
    -0.06
    POSITIVE LOGITS
     ترک
    0.07
     ภาษ
    0.07
    subj
    0.06
    _PUSHDATA
    0.06
    _NEAREST
    0.06
     �
    0.06
     perpetual
    0.06
     +:+
    0.06
     Hogwarts
    0.06
     temporada
    0.06
    Act Density 0.001%

    No Known Activations