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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ука
    -0.07
     grandes
    -0.07
    away
    -0.07
    vae
    -0.06
    LOT
    -0.06
    иму
    -0.06
     withhold
    -0.06
    qué
    -0.06
    lal
    -0.06
     Slot
    -0.06
    POSITIVE LOGITS
    ,assign
    0.07
     scrollTop
    0.07
    _inside
    0.06
    효
    0.06
    سال
    0.06
     issued
    0.06
    .rec
    0.06
    σιμο
    0.06
    ,W
    0.06
    
    0.06
    Act Density 0.028%

    No Known Activations