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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of uncertainty

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

    Sentences including the question "what am I"

    np_acts-logits-general · gemini-2.0-flash

    am I doing wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     my
    -1.04
     myself
    -0.86
    my
    -0.84
     mich
    -0.84
     meinen
    -0.79
     meine
    -0.78
     mijn
    -0.78
     mine
    -0.77
     meu
    -0.77
     minha
    -0.77
    POSITIVE LOGITS
     I
    2.40
    I
    1.28
     i
    1.04
     я
    1.00
    Ｉ
    0.79
    ]")]
    0.73
    Ⅰ
    0.71
     незавершена
    0.69
    ագրություններ
    0.66
     मैं
    0.65
    Act Density 0.736%

    No Known Activations