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

    Neuronpedia

    INDEX
    Explanations

    $casts and $primaryKey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     associée
    0.44
    𝕨
    0.40
    бою
    0.40
    挂
    0.38
    𝙨
    0.38
    𝘺
    0.38
     associé
    0.38
    pá
    0.38
    掛
    0.37
    moins
    0.37
    POSITIVE LOGITS
     cast
    0.68
     casts
    0.67
    casts
    0.63
     Cast
    0.59
    CAST
    0.52
     HID
    0.52
     CAST
    0.51
     casting
    0.51
    cast
    0.50
    Cast
    0.50
    Act Density 0.001%

    No Known Activations