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

    Neuronpedia

    INDEX
    Explanations

    emphasized terms and phrases that indicate specificity or heightened concern in a text

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

    intensifier followed by when/in/since/for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bra
    -0.49
     cow
    -0.43
    script
    -0.41
     Cow
    -0.40
     swe
    -0.39
    AudioSource
    -0.39
    IContainer
    -0.38
     dra
    -0.37
    fest
    -0.37
     sco
    -0.37
    POSITIVE LOGITS
    RenderAtEndOf
    0.58
    Билгалдахарш
    0.54
     wanneer
    0.52
    AndEndTag
    0.52
     przypadku
    0.52
     wśród
    0.51
     geldt
    0.51
     مشين
    0.51
     đối
    0.51
     ivelany
    0.50
    Act Density 0.063%

    No Known Activations