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

    Neuronpedia

    INDEX
    Explanations

    sections and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ˆ
    0.50
    પ
    0.47
    oselect
    0.45
     масштаб
    0.43
     Educación
    0.43
    떤
    0.43
    acidad
    0.42
    itación
    0.42
    forderungen
    0.42
     основной
    0.42
    POSITIVE LOGITS
     jell
    0.45
     newly
    0.44
     nul
    0.41
     gul
    0.41
    Remote
    0.41
    Neutral
    0.40
    Standard
    0.40
    旗
    0.40
     stools
    0.40
     dll
    0.39
    Act Density 0.004%

    No Known Activations