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

    Neuronpedia

    INDEX
    Explanations

    la following nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.41
    l
    0.36
    d
    0.34
    n
    0.34
     allerlei
    0.33
    g
    0.33
    the
    0.32
    r
    0.31
    -
    0.30
    这里
    0.29
    POSITIVE LOGITS
     misma
    0.44
     mismas
    0.41
     costumbres
    0.36
     propia
    0.34
     posibilidad
    0.34
    на
    0.33
     importancia
    0.33
     experiencia
    0.33
     coward
    0.33
     mucosa
    0.33
    Act Density 0.198%

    No Known Activations