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

    Neuronpedia

    INDEX
    Explanations

    ways to frame questions about potential solutions or methods

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

    any way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.48
    !*\
    -0.44
    scribers
    -0.37
     yyj
    -0.37
    aff
    -0.35
    astéro
    -0.34
     تانيه
    -0.34
    şiv
    -0.34
    addComponent
    -0.33
     Wa
    -0.33
    POSITIVE LOGITS
    GEBURTSDATUM
    0.56
    rungsseite
    0.55
     any
    0.54
    
    0.52
     quelcon
    0.52
     quelconque
    0.50
     quaisquer
    0.50
     qualquer
    0.48
    Tembelea
    0.48
    IntoConstraints
    0.47
    Act Density 0.082%

    No Known Activations