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

    Neuronpedia

    INDEX
    Explanations

    phrases containing "history", "in", and location words

    oai_token-act-pair · gemini-2.0-flash

    history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.45
    tvguidetime
    -0.44
    SpringBootTest
    -0.42
     mourir
    -0.42
    ardı
    -0.42
    รอง
    -0.41
    CppCodeGen
    -0.41
    wesenheit
    -0.40
     sonrisa
    -0.39
     confiança
    -0.39
    POSITIVE LOGITS
     history
    2.23
    history
    1.88
     History
    1.80
     HISTORY
    1.72
    History
    1.71
     historia
    1.55
    HISTORY
    1.54
     sejarah
    1.51
     historie
    1.49
     histories
    1.46
    Act Density 0.803%

    No Known Activations