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

    Neuronpedia

    INDEX
    Explanations

    declare block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sabiduría
    0.70
     personalità
    0.70
    ትክል
    0.69
     sustancias
    0.65
    ALTERNATIV
    0.65
     Gottes
    0.64
     speechSynthesis
    0.64
     publicité
    0.63
     sistemat
    0.63
     tecnici
    0.63
    POSITIVE LOGITS
     x
    1.38
    x
    1.08
     p
    1.07
     s
    1.03
     obj
    1.01
     v
    1.01
     r
    0.97
     k
    0.96
     d
    0.95
     tmp
    0.94
    Act Density 0.941%

    No Known Activations