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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods or eras

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

    early and late contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valent
    -0.45
     Biôgrafia
    -0.40
     extern
    -0.37
     Bolívar
    -0.34
    VersionUID
    -0.34
    mybatisplus
    -0.33
     sement
    -0.33
     EXTERNAL
    -0.33
    aarrggbb
    -0.32
     Atom
    -0.32
    POSITIVE LOGITS
    early
    0.82
     early
    0.81
     late
    0.73
    Early
    0.71
     Early
    0.68
     LATE
    0.66
     Late
    0.66
     frühen
    0.65
    Late
    0.65
     temprano
    0.65
    Act Density 0.058%

    No Known Activations