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

    Neuronpedia

    INDEX
    Explanations

    textual formatting or structure

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

    Non-English text/characters

    np_acts-logits-general · gemini-2.0-flash

    Japanese names and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.67
    y
    -0.63
     in
    -0.63
     y
    -0.63
     t
    -0.61
     j
    -0.61
     to
    -0.61
     de
    -0.61
     be
    -0.60
     $\
    -0.60
    POSITIVE LOGITS
     يتيمه
    1.47
     myſelf
    1.30
     Theſe
    1.26
     незавершена
    1.24
     كومونز
    1.24
    MemoryWarning
    1.24
    GraphicsUnit
    1.22
     '\\;'
    1.22
    CloseOperation
    1.21
     crdi
    1.20
    Act Density 0.029%

    No Known Activations