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

    Neuronpedia

    INDEX
    Explanations

    personalized items and multilingual contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unin
    0.36
    contiguous
    0.35
    efficient
    0.33
    onin
    0.33
    tes
    0.32
     standby
    0.32
    f
    0.32
    効率
    0.31
    omit
    0.31
     longitudinal
    0.31
    POSITIVE LOGITS
     accessoires
    0.51
     personnaliser
    0.48
     personalizar
    0.46
     verschiedene
    0.45
     çeşitli
    0.45
     acompañado
    0.45
    𝖆
    0.45
     personnalisé
    0.44
     accompagné
    0.44
     accessori
    0.43
    Act Density 0.066%

    No Known Activations