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

    Neuronpedia

    INDEX
    Explanations

    biographies and historical figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.20
    +
    0.18
    :
    0.18
    i
    0.17
    ok
    0.17
    ikawa
    0.17
    ah
    0.17
    aman
    0.17
    ifik
    0.17
    res
    0.17
    POSITIVE LOGITS
     cheered
    0.16
     Algonquin
    0.16
     Sitio
    0.16
    ."},
    0.16
     Fontainebleau
    0.15
     Dharm
    0.15
    followlike
    0.15
     seizoen
    0.15
     Ministro
    0.15
     Palmyra
    0.15
    Act Density 0.000%

    No Known Activations