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

    Neuronpedia

    INDEX
    Explanations

    offering more or asking to try

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplemente
    0.48
     simplement
    0.46
     Просто
    0.44
     පමණ
    0.44
     просто
    0.43
     tertentu
    0.43
     lihtsalt
    0.42
     잠깐
    0.42
     prostu
    0.42
     simplesmente
    0.42
    POSITIVE LOGITS
    see
    0.59
     see
    0.54
     secrets
    0.52
     critique
    0.51
     scandalous
    0.51
     critiques
    0.50
     interpretations
    0.49
     theories
    0.49
     dissection
    0.49
     confrontations
    0.49
    Act Density 0.007%

    No Known Activations