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

    Neuronpedia

    INDEX
    Explanations

    instances of technical jargon or code-related terms

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

    Net, HDR, MEM, api, management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     îna
    -0.32
    ニア
    -0.27
     authorities
    -0.26
     paraître
    -0.24
    地说道
    -0.23
     ciudadana
    -0.23
     autoridades
    -0.23
     peito
    -0.22
     rẻ
    -0.22
     twar
    -0.21
    POSITIVE LOGITS
    RenderAtEndOf
    0.83
     CURIAM
    0.75
     wireType
    0.73
    EDEFAULT
    0.72
    久しぶ
    0.71
    ロウィン
    0.70
     Italijanski
    0.69
     AssemblyCulture
    0.68
    <unused41>
    0.67
    <unused47>
    0.67
    Act Density 0.161%

    No Known Activations