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

    Neuronpedia

    INDEX
    Explanations

    words related to animal species and their classifications

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

    Follows "an", "uran", "than", "guan", or "zan"

    np_acts-logits-general · gemini-2.0-flash

    words ending in an and then certain suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yue
    -0.68
    tent
    -0.68
    y
    -0.67
    t
    -0.65
    tor
    -0.64
    tes
    -0.61
    tons
    -0.61
    tro
    -0.61
    tend
    -0.61
    sound
    -0.59
    POSITIVE LOGITS
    er
    0.71
     Tana
    0.66
    ufact
    0.65
    ews
    0.64
     Constitucional
    0.62
    ning
    0.59
    alysis
    0.57
    ek
    0.57
     Plen
    0.57
     tongs
    0.56
    Act Density 0.293%

    No Known Activations