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

    Neuronpedia

    INDEX
    Explanations

    -powered/-driven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ending
    -0.07
    ificates
    -0.07
    larını
    -0.07
    /device
    -0.06
    .googleapis
    -0.06
    Công
    -0.06
    λής
    -0.06
     vente
    -0.06
     bước
    -0.06
    .**************↵
    -0.06
    POSITIVE LOGITS
     stacked
    0.08
    -themed
    0.07
     stmt
    0.07
    →
    0.07
    _Not
    0.06
     legit
    0.06
    -focused
    0.06
    urable
    0.06
    -width
    0.06
     ObjectType
    0.06
    Act Density 0.140%

    No Known Activations