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

    Neuronpedia

    INDEX
    Explanations

    allows you to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anday
    0.45
    负担
    0.45
    itarian
    0.45
    rito
    0.42
     ना
    0.42
     exclusivamente
    0.42
    imately
    0.41
    मात्र
    0.41
    azir
    0.41
    cookieParser
    0.40
    POSITIVE LOGITS
     a
    0.55
     trophic
    0.47
     rabbit
    0.44
     recombin
    0.43
     Rabbit
    0.43
     Wolf
    0.43
     arugula
    0.41
     Music
    0.41
     mighty
    0.39
     Wilhelm
    0.39
    Act Density 0.001%

    No Known Activations