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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to scientific or chemical substances and ingredients

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

    ending with "an" or "wan"

    np_acts-logits-general · gemini-2.0-flash

    ending in an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    guang
    -0.66
    tent
    -0.66
    yue
    -0.65
    sound
    -0.64
    dummy
    -0.63
    guo
    -0.62
    tons
    -0.61
    governmental
    -0.60
    tro
    -0.60
    gico
    -0.60
    POSITIVE LOGITS
    ek
    0.75
    er
    0.72
    ews
    0.70
    ning
    0.67
    alysis
    0.65
    ey
    0.61
    en
    0.61
    ufact
    0.60
    ner
    0.60
    ny
    0.58
    Act Density 0.291%

    No Known Activations