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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting elements commonly used in mathematical equations or programming code

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

    academic paper citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.48
    ArgsConstructor
    -0.37
    wpi
    -0.35
    vertx
    -0.35
     Spot
    -0.35
     Rake
    -0.35
    ToLower
    -0.34
    Spot
    -0.34
     Charm
    -0.34
     rig
    -0.33
    POSITIVE LOGITS
     leaſt
    0.57
    aarrggbb
    0.56
     eſſ
    0.55
     ſou
    0.51
     abſ
    0.50
     ſtate
    0.49
     tää
    0.48
     ſta
    0.48
     Eſ
    0.47
     ainfi
    0.47
    Act Density 0.004%

    No Known Activations