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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tricks
    -0.07
    -save
    -0.07
     '>
    -0.07
     burgeoning
    -0.07
     settled
    -0.07
    odule
    -0.06
     askeri
    -0.06
     bub
    -0.06
     precautions
    -0.06
    $array
    -0.06
    POSITIVE LOGITS
    ixo
    0.07
     实
    0.07
    ingga
    0.07
     месяцев
    0.07
     菲律宾
    0.06
     în
    0.06
     zurück
    0.06
    _THEME
    0.06
    IN
    0.06
    ीवन
    0.06
    Act Density 0.034%

    No Known Activations