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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research methodologies and findings

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

    scientific research mechanisms and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.76
     Wikimedijinoj
    -0.52
     intptr
    -0.49
     ſte
    -0.45
    󠁢
    -0.45
    Gön
    -0.44
     HasFactory
    -0.44
    httphttps
    -0.44
     betweenstory
    -0.44
    rungsseite
    -0.43
    POSITIVE LOGITS
    省市镇
    0.48
    ArrowToggle
    0.41
    Application
    0.38
    ModelSerializer
    0.37
    algorithm
    0.37
    GEBURTSDATUM
    0.36
     <>",
    0.36
     Characteristic
    0.35
    Characteristic
    0.35
    发表于
    0.35
    Act Density 0.087%

    No Known Activations