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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific identifiers within the text

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

    foreign words or technical jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.93
    setVerticalGroup
    -0.84
    CloseOperation
    -0.78
    AnchorStyles
    -0.78
     defaultstate
    -0.75
    RectangleBorder
    -0.72
    awtextra
    -0.71
    httphttps
    -0.69
    DockStyle
    -0.69
    IntoConstraints
    -0.69
    POSITIVE LOGITS
     larmes
    0.40
     gadis
    0.35
     Förderung
    0.32
     avanzada
    0.32
     pedagang
    0.31
     cedera
    0.30
     poches
    0.30
     rijk
    0.29
    igshid
    0.29
     Planung
    0.29
    Act Density 0.001%

    No Known Activations