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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and moments of reflective thought

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

    sequence of actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abestanden
    -0.56
     незавершена
    -0.56
    PYX
    -0.55
     gevolg
    -0.53
     盗撮
    -0.51
    Tikang
    -0.51
     виправивши
    -0.50
     affari
    -0.50
    ruct
    -0.49
    ACJA
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.36
     slight
    0.33
    Bigr
    0.33
     supli
    0.31
    icoot
    0.30
     seeming
    0.29
     EconPapers
    0.29
     motion
    0.29
     once
    0.28
     reacting
    0.28
    Act Density 0.051%

    No Known Activations