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

    Neuronpedia

    INDEX
    Explanations

    hydrogen peroxide

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical compounds and reactions, particularly hydrogen peroxide.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    at
    -2.34
     they
    -2.28
    er
    -2.27
    .”
    -2.25
    1
    -2.23
    D
    -2.09
    f
    -2.05
    ou
    -1.99
    I
    -1.96
     возле
    -1.94
    POSITIVE LOGITS
    ↵
    2.48
    蓠
    2.22
    BEAT
    2.11
    姈
    2.05
     Они
    2.02
    踭
    2.00
    他们是
    1.95
    1.95
    𝓚
    1.95
    laient
    1.93
    Act Density 0.019%

    No Known Activations