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

    Neuronpedia

    INDEX
    Explanations

    references to the Hiroshima and Nagasaki bombings

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

    Hiroshima bombing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.38
    InjectAttribute
    -0.37
    DataSnapshot
    -0.34
     "..\..\
    -0.33
    ("~/
    -0.33
     createSlice
    -0.33
     Colección
    -0.32
    WithMany
    -0.31
     "..\..\..\
    -0.31
     attempted
    -0.30
    POSITIVE LOGITS
     estekak
    1.34
     Hiroshima
    0.97
     Picchu
    0.96
    schild
    0.88
     لينك
    0.79
    InputBorder
    0.77
    Hiros
    0.69
     nakalista
    0.64
    -------------</
    0.62
     Nagasaki
    0.60
    Act Density 0.003%

    No Known Activations