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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and surnames

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

    Two-letter combinations at the end of words

    np_acts-logits-general · gemini-2.0-flash

    skyOff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.71
    PhysRev
    -0.70
    matchCondition
    -0.60
    +#+#
    -0.56
    ैसे
    -0.54
    Schematic
    -0.54
    ganj
    -0.54
    كويكب
    -0.53
    ovým
    -0.53
    PRNewswire
    -0.52
    POSITIVE LOGITS
    sky
    0.66
    off
    0.66
    ny
    0.55
    ky
    0.53
    ksi
    0.53
     referenties
    0.51
    ksy
    0.50
    וב
    0.49
    OFF
    0.48
     Off
    0.47
    Act Density 0.236%

    No Known Activations