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

    Neuronpedia

    INDEX
    Explanations

    instances of significant transitions or revelations in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    initiating first person statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XtraBars
    -0.43
    öglichkeiten
    -0.42
     also
    -0.41
    ᅠ
    -0.39
    angliski
    -0.39
     tư
    -0.39
     également
    -0.39
     Chwiliwch
    -0.39
    WithMany
    -0.38
    одно
    -0.38
    POSITIVE LOGITS
    ngdoc
    0.53
    transQ
    0.50
    WithIOException
    0.48
    contentLoaded
    0.48
    featureID
    0.47
    ⟬
    0.45
    0.43
    újo
    0.43
    ſelf
    0.43
    LabelTagHelper
    0.42
    Act Density 0.048%

    No Known Activations