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

    Neuronpedia

    INDEX
    Explanations

    visual representations or diagrams and their captions in a text

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

    Symbols inside parentheses/brackets

    np_acts-logits-general · gemini-2.0-flash

    symbols and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.75
    "},
    -0.73
    WebControls
    -0.72
    ".
    -0.69
     Roskov
    -0.69
    存于互联网档案馆
    -0.69
    SequentialGroup
    -0.69
    IBOutlet
    -0.68
    '],
    -0.68
    .";
    -0.68
    POSITIVE LOGITS
     >>
    0.51
    굴
    0.49
    ่า
    0.46
     ostr
    0.45
    grafi
    0.44
    nski
    0.44
     CPT
    0.44
    ровок
    0.43
     o
    0.43
    ף
    0.43
    Act Density 0.128%

    No Known Activations