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

    Neuronpedia

    INDEX
    Explanations

    animals or actions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LER
    0.86
    बिन
    0.84
    lach
    0.84
    inat
    0.82
    szer
    0.82
    isent
    0.81
    Lewis
    0.80
    lés
    0.80
    ícul
    0.79
    iam
    0.78
    POSITIVE LOGITS
     k
    0.83
     bowed
    0.82
     cows
    0.77
     tid
    0.74
     mushrooms
    0.71
     considered
    0.70
     bowing
    0.70
     herds
    0.70
     hurried
    0.69
     bombarded
    0.68
    Act Density 0.000%

    No Known Activations