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

    Neuronpedia

    INDEX
    Explanations

    different implementations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     luxe
    0.48
     glimmer
    0.46
    Callories
    0.44
     totalité
    0.44
    同比增长
    0.42
     Kurds
    0.42
     shelter
    0.41
     glitter
    0.41
    Princess
    0.41
    ínsula
    0.41
    POSITIVE LOGITS
    あら
    0.47
     Narrative
    0.43
     Evaluations
    0.43
    ariu
    0.42
     過
    0.41
     interactions
    0.41
    observ
    0.40
    ದಾರ
    0.40
    abolic
    0.40
     permissive
    0.40
    Act Density 0.008%

    No Known Activations