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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions and academic programs

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

    filenames and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.56
    saraba
    -0.51
    Населення
    -0.47
    Personendaten
    -0.45
     createSlice
    -0.40
    makeConstraints
    -0.38
    ellement
    -0.38
    읍
    -0.37
    RegressionTest
    -0.37
    esModule
    -0.36
    POSITIVE LOGITS
    ########.
    0.53
    InjectAttribute
    0.47
    rungsseite
    0.46
    ForValue
    0.43
    phosa
    0.42
    rrggbb
    0.40
     civili
    0.40
     pygame
    0.40
    messageInfo
    0.40
     vinyle
    0.39
    Act Density 0.520%

    No Known Activations