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

    Neuronpedia

    INDEX
    Explanations

    configuration files and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    0.42
    ́i
    0.41
    ﻷ
    0.40
    ujuan
    0.40
    バイト
    0.39
    áil
    0.39
     Беларусі
    0.39
    öt
    0.39
    ΑΣ
    0.39
    ades
    0.38
    POSITIVE LOGITS
     Loki
    0.46
    DIRECT
    0.45
     estimator
    0.43
     secrétaire
    0.43
     Model
    0.42
    DA
    0.41
    दार
    0.41
     সন্দ
    0.41
    㡚
    0.41
     stormy
    0.40
    Act Density 0.006%

    No Known Activations