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

    Neuronpedia

    INDEX
    Explanations

    assertive statements and expressions of personal beliefs or experiences

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

    following expletives

    np_acts-logits-general · gemini-2.0-flash

    GET OUT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.94
     محفوظة
    -0.94
    帖最后由
    -0.88
     typelib
    -0.84
     Paglinawan
    -0.84
    RTSC
    -0.83
    OGND
    -0.78
    balleur
    -0.78
    CloseOperation
    -0.78
     كومونز
    -0.77
    POSITIVE LOGITS
     fucking
    1.07
     FUCKING
    0.93
    fucking
    0.84
     freakin
    0.84
    .
    0.81
     goddamn
    0.81
     Fucking
    0.79
     freaking
    0.78
     fuckin
    0.77
     absolutely
    0.75
    Act Density 0.389%

    No Known Activations