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

    Neuronpedia

    INDEX
    Explanations

    disputas, paradigmas, transcripción

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ING
    0.62
     AND
    0.58
     First
    0.58
    0.57
    :
    0.57
     Expl
    0.52
     rep
    0.52
     Appro
    0.51
     OR
    0.51
    ANDS
    0.51
    POSITIVE LOGITS
    ografía
    1.14
    ografia
    1.08
    ología
    1.03
    rétaire
    0.97
    atividade
    0.94
    usuario
    0.94
    🤛
    0.94
    ificación
    0.93
    💹
    0.93
    direccion
    0.92
    Act Density 0.345%

    No Known Activations