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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations, particularly involving symbols and equations

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

    LaTeX math mode: `${`

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math symbols and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.61
    ⓧ
    -0.58
    unknownFields
    -0.55
    tagHelperRunner
    -0.51
    HWND
    -0.49
     Pal
    -0.49
    ッタ
    -0.49
    Pal
    -0.48
    penup
    -0.47
    uxxxx
    -0.47
    POSITIVE LOGITS
    writeFieldEnd
    0.64
     pleaſure
    0.62
     myſelf
    0.60
     متعلقه
    0.59
     المعيارى
    0.58
     ſche
    0.58
    sedown
    0.58
     programmet
    0.57
    tvguidetime
    0.56
    erapeu
    0.56
    Act Density 0.415%

    No Known Activations