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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence termination markers

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

    Followed by a question word

    np_acts-logits-general · gemini-2.0-flash

    let's get started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niająca
    -0.56
    我在
    -0.53
    typeorm
    -0.50
    💔
    -0.50
    😞
    -0.50
    dimos
    -0.49
     myself
    -0.49
    😩
    -0.48
    ]--;
    -0.47
    私には
    -0.47
    POSITIVE LOGITS
     Plus
    0.93
    Plus
    0.89
    さあ
    0.83
     Enjoy
    0.77
    さぁ
    0.75
    Ready
    0.75
     Alors
    0.74
    brigens
    0.74
     Want
    0.73
     don
    0.72
    Act Density 0.111%

    No Known Activations