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

    Neuronpedia

    INDEX
    Explanations

    multi-word phrases and designations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ork
    0.80
     Sour
    0.72
     sugar
    0.72
    sour
    0.70
     cStart
    0.70
    Ore
    0.69
    Qu
    0.68
    ೂ
    0.67
    Sour
    0.66
    Sugar
    0.66
    POSITIVE LOGITS
     discriminatory
    0.86
     définie
    0.80
     definido
    0.78
     bienvenue
    0.77
    ppet
    0.76
    ệm
    0.76
    मुखी
    0.75
     multipart
    0.74
     definida
    0.74
     lindos
    0.74
    Act Density 0.000%

    No Known Activations