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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _disabled
    -0.08
     Eagles
    -0.07
    לית
    -0.07
    -layout
    -0.07
     dấu
    -0.07
    龅
    -0.07
    ypes
    -0.07
     bữa
    -0.07
    cname
    -0.07
    ߡ
    -0.07
    POSITIVE LOGITS
    nw
    0.08
    IntegerField
    0.08
     mar
    0.07
    _container
    0.07
    浸
    0.07
     чувство
    0.07
    jo
    0.07
    writer
    0.07
     -------↵
    0.07
     bei
    0.07
    Act Density 0.003%

    No Known Activations