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

    Neuronpedia

    INDEX
    Explanations

    , where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Angebote
    0.81
    ministerium
    0.80
     Martine
    0.78
     اكو
    0.75
     reiterate
    0.75
    帮你
    0.74
    RequestMethod
    0.74
    ContextCompat
    0.73
    elwv
    0.73
     veniam
    0.73
    POSITIVE LOGITS
     about
    0.72
    about
    0.66
    事人
    0.65
     About
    0.65
    About
    0.64
     вскоре
    0.63
    めに
    0.63
    \{
    0.63
    cesa
    0.63
    zca
    0.61
    Act Density 0.014%

    No Known Activations