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

    Neuronpedia

    INDEX
    Explanations

    .x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tensor
    -0.08
    舌尖
    -0.07
    (serializers
    -0.07
    hidden
    -0.07
    (elements
    -0.07
     SKIP
    -0.07
     Gloss
    -0.07
    探究
    -0.07
     lightning
    -0.07
     triggering
    -0.06
    POSITIVE LOGITS
    arat
    0.07
    вел
    0.07
    apa
    0.07
    耢
    0.06
    Ranked
    0.06
    .va
    0.06
     coût
    0.06
    솨
    0.06
     Bun
    0.06
    maid
    0.06
    Act Density 0.009%

    No Known Activations