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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     srdce
    -0.07
     SAR
    -0.07
     kara
    -0.07
    มต
    -0.07
     gums
    -0.07
    átky
    -0.07
     καν
    -0.07
     Mädchen
    -0.06
    ันยายน
    -0.06
     dile
    -0.06
    POSITIVE LOGITS
     weight
    0.15
     Weight
    0.13
    Weight
    0.12
    weight
    0.10
    -weight
    0.10
     WEIGHT
    0.10
    _weight
    0.09
    weights
    0.09
     We
    0.08
    (weight
    0.08
    Act Density 0.022%

    No Known Activations