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

    Neuronpedia

    INDEX
    Explanations

    concepts related to health and biological responses

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

    a reason or explanation

    np_acts-logits-general · gemini-2.0-flash

    explains why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.81
     pleaſure
    -0.78
    bootstrapcdn
    -0.78
    ſelf
    -0.76
     itſelf
    -0.74
     themſelves
    -0.73
     Majefty
    -0.73
     Houſe
    -0.71
     himſelf
    -0.70
     houſe
    -0.69
    POSITIVE LOGITS
     why
    1.27
     explains
    1.15
     reason
    1.07
     explain
    1.03
     explanation
    1.03
    why
    1.02
    难怪
    1.01
     explaining
    0.97
     pourquoi
    0.97
     Why
    0.93
    Act Density 0.433%

    No Known Activations