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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize significant parts or moments in a narrative

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

    the best part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abonnez
    -0.42
    thető
    -0.42
    jooq
    -0.38
    IntoConstraints
    -0.38
     citoy
    -0.38
     noDo
    -0.37
     Vereine
    -0.37
     évêque
    -0.36
     kommunen
    -0.35
     længere
    -0.35
    POSITIVE LOGITS
     part
    0.56
    part
    0.55
    Part
    0.54
     Part
    0.54
     parts
    0.51
     Parts
    0.50
     parte
    0.49
    featureID
    0.49
    SceneManagement
    0.49
    centralwidget
    0.48
    Act Density 0.009%

    No Known Activations