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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乡
    -0.07
    优势
    -0.06
    тия
    -0.06
     cuatro
    -0.06
    販売
    -0.06
    출장
    -0.06
     Guam
    -0.06
    าของ
    -0.06
    ौ
    -0.06
     arguing
    -0.05
    POSITIVE LOGITS
     devastation
    0.07
     insulation
    0.07
    ><!--
    0.07
    PHA
    0.07
    mí
    0.07
    azio
    0.06
    ollections
    0.06
    spor
    0.06
     offs
    0.06
    rego
    0.06
    Act Density 0.004%

    No Known Activations