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

    Neuronpedia

    INDEX
    Explanations

    much

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,row
    -0.06
    )+"
    -0.06
    ====
    -0.06
    tual
    -0.06
     vå
    -0.06
    ,”
    -0.06
     ====
    -0.06
    uite
    -0.06
     evaluations
    -0.06
    ,width
    -0.06
    POSITIVE LOGITS
    dis
    0.07
     ragazzi
    0.07
    animations
    0.07
    媒
    0.07
     Discrim
    0.07
     propor
    0.06
    _BUCKET
    0.06
     forc
    0.06
     вони
    0.06
    _metric
    0.06
    Act Density 0.003%

    No Known Activations