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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testimon
    -0.07
    .abspath
    -0.07
    Rail
    -0.07
    стре
    -0.06
     smlouvy
    -0.06
    มากกว
    -0.06
    >",
    -0.06
    ships
    -0.06
    trad
    -0.06
    Ster
    -0.06
    POSITIVE LOGITS
     hiss
    0.06
    onsense
    0.06
     Being
    0.06
     Tri
    0.06
     Vinyl
    0.06
     Valor
    0.06
    stown
    0.06
    ۷
    0.06
     Cone
    0.06
    /map
    0.06
    Act Density 0.000%

    No Known Activations