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

    Neuronpedia

    INDEX
    Explanations

    movie titles and song lyrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferram
    0.34
     computational
    0.33
     granularity
    0.33
     hinsichtlich
    0.32
     azalt
    0.32
     metri
    0.32
     effectuer
    0.32
     macrom
    0.31
     manejar
    0.31
     gebruikers
    0.31
    POSITIVE LOGITS
    u
    0.36
    un
    0.35
    yn
    0.35
    is
    0.34
    il
    0.34
    ite
    0.34
    id
    0.34
    ip
    0.34
    ys
    0.34
    im
    0.33
    Act Density 0.122%

    No Known Activations