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

    Neuronpedia

    INDEX
    Explanations

    async Task methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Model
    0.59
    ka
    0.57
    Object
    0.56
     Cuban
    0.55
     Burnham
    0.55
    胿
    0.54
     Bolton
    0.54
     Model
    0.53
    keleton
    0.53
    left
    0.52
    POSITIVE LOGITS
     valeurs
    0.61
     ordinate
    0.60
     diffuse
    0.58
     divergences
    0.58
     sociaux
    0.56
     outperform
    0.56
     över
    0.56
     utiliser
    0.55
    エ
    0.55
     répondre
    0.54
    Act Density 0.008%

    No Known Activations