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

    Neuronpedia

    INDEX
    Explanations

    Contains numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	x
    -0.06
    Regional
    -0.06
     años
    -0.06
    高校
    -0.06
     incap
    -0.06
     ethn
    -0.06
     dansk
    -0.06
     habitual
    -0.06
     Publisher
    -0.05
    <Any
    -0.05
    POSITIVE LOGITS
    oglob
    0.07
    edes
    0.07
    nement
    0.07
    gel
    0.06
    (System
    0.06
    _zip
    0.06
    льт
    0.06
    Sys
    0.06
    ramid
    0.06
    ्ड
    0.06
    Act Density 0.016%

    No Known Activations