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

    Neuronpedia

    INDEX
    Explanations

    coordinating conjunctions that indicate connections or relationships in the text

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

    actions and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Polsek
    -0.42
     orejas
    -0.42
     casquette
    -0.40
     esimer
    -0.40
     myö
    -0.39
     Verhält
    -0.38
     arvio
    -0.37
     roupa
    -0.36
     semuanya
    -0.35
     sosok
    -0.35
    POSITIVE LOGITS
    awtextra
    0.66
     invokingState
    0.66
     المعيارى
    0.63
    Demografie
    0.61
    ftagPool
    0.60
    ArgsConstructor
    0.59
    setVerticalGroup
    0.58
    bcryptjs
    0.58
     ſever
    0.57
    extAlignment
    0.57
    Act Density 0.027%

    No Known Activations