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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Su
    -0.07
    _Se
    -0.07
    Rich
    -0.07
    .X
    -0.07
    Anal
    -0.07
     Chem
    -0.06
     chac
    -0.06
     pa
    -0.06
    維
    -0.06
    _folder
    -0.06
    POSITIVE LOGITS
    dě
    0.06
    ồng
    0.06
    어요
    0.06
     운
    0.06
    験
    0.06
    bindValue
    0.06
    boxing
    0.06
     occupants
    0.06
    (formatter
    0.06
    ocus
    0.06
    Act Density 0.056%

    No Known Activations