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

    Neuronpedia

    INDEX
    Explanations

    narrative elements that indicate completion or finished actions

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

    End of a multi-step instruction

    np_acts-logits-general · gemini-2.0-flash

    completion and finality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ErrInvalid
    -0.54
     leeftijd
    -0.47
     invloed
    -0.45
     protoimpl
    -0.43
     $_(
    -0.43
     väli
    -0.43
     getAge
    -0.43
     slecht
    -0.43
    httphttps
    -0.43
     współpra
    -0.42
    POSITIVE LOGITS
     voila
    0.54
    Voila
    0.49
     Voilà
    0.48
     voilà
    0.47
    Bam
    0.47
     Presto
    0.46
    Voilà
    0.45
    principalTable
    0.45
    Done
    0.44
     presto
    0.44
    Act Density 0.244%

    No Known Activations