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

    Neuronpedia

    INDEX
    Explanations

    code snippets/excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profound
    -0.07
     kå
    -0.06
     Evaluate
    -0.06
     Pav
    -0.06
    يلا
    -0.06
     Có
    -0.06
     Raj
    -0.06
    ="/"
    -0.06
    芙
    -0.06
     prostoru
    -0.06
    POSITIVE LOGITS
    depart
    0.07
     öğretmen
    0.07
     go
    0.07
    renders
    0.06
    IENCE
    0.06
    /update
    0.06
    惠
    0.06
    UP
    0.06
    stdClass
    0.06
     منزل
    0.06
    Act Density 0.000%

    No Known Activations