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

    Neuronpedia

    INDEX
    Explanations

    mathematical relationships and operations

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

    let variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.58
    uate
    -0.50
    Slf
    -0.48
    bootstrapcdn
    -0.47
     ब्रेकडाउन
    -0.46
    kespeare
    -0.45
    cente
    -0.45
     itemName
    -0.44
     quis
    -0.43
    ecology
    -0.43
    POSITIVE LOGITS
     strá
    0.37
     adjunto
    0.36
     alike
    0.35
    parsedMessage
    0.34
     siquiera
    0.34
     uzupeł
    0.33
     espectáculos
    0.33
    ECTS
    0.33
    kmale
    0.33
     somehow
    0.33
    Act Density 0.047%

    No Known Activations