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

    Neuronpedia

    INDEX
    Explanations

    the word "neutral" and words related to it

    oai_token-act-pair · gemini-2.0-flash

    neutral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.16
    }")
    -1.11
     ſche
    -1.01
     $_"
    -0.98
     betweenstory
    -0.97
    ']))
    -0.96
    ".
    -0.96
     Theſe
    -0.95
     dieß
    -0.94
    lapsingToolbar
    -0.94
    POSITIVE LOGITS
    <eos>
    0.83
    1
    0.73
    0
    0.68
    3
    0.68
     (
    0.67
    2
    0.66
    ↵
    0.66
    </td>
    0.63
    4
    0.59
    5
    0.59
    Act Density 2.592%

    No Known Activations