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

    Neuronpedia

    INDEX
    Explanations

    conversational dialogue and interactions

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

    dialog quotes with speakers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.71
    AccessorTable
    -0.63
    LookAnd
    -0.63
    fjspx
    -0.62
    ByVersion
    -0.60
    GraphicsUnit
    -0.58
    ValueStyle
    -0.58
    exitRule
    -0.57
     تعدى
    -0.56
    PerformLayout
    -0.55
    POSITIVE LOGITS
    phy
    0.36
     Infórmanos
    0.36
     Saw
    0.33
     complain
    0.31
     Fowler
    0.31
     swine
    0.31
     fired
    0.31
     Насе
    0.30
     gw
    0.30
     dies
    0.30
    Act Density 0.030%

    No Known Activations