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

    Neuronpedia

    INDEX
    Explanations

    titles of films and works related to crime and action genres

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

    Movie or film titles

    np_acts-logits-general · gemini-2.0-flash

    movie titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.53
    -
    -0.52
    <eos>
    -0.51
     mắn
    -0.49
    [
    -0.48
     umane
    -0.48
     consistently
    -0.47
    Yep
    -0.47
    ureusement
    -0.45
     "
    -0.44
    POSITIVE LOGITS
     Houſe
    0.85
    Filmographie
    0.76
     Majefty
    0.73
     Theſe
    0.72
     című
    0.72
    TypedDataSet
    0.71
     myſelf
    0.69
     שוליים
    0.67
    ſelf
    0.66
    Obrázky
    0.66
    Act Density 0.169%

    No Known Activations