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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or questioning regarding understanding

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

    Expressing confusion or lack of understanding

    np_acts-logits-general · gemini-2.0-flash

    understanding why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ja
    -0.45
    DockStyle
    -0.44
     provisoire
    -0.42
    setopt
    -0.42
    aka
    -0.41
     εμπ
    -0.41
    võ
    -0.40
     terce
    -0.40
     bäst
    -0.39
     masas
    -0.39
    POSITIVE LOGITS
     inexplicable
    1.14
     illogical
    1.09
     puzzling
    1.07
     why
    1.06
     baffling
    1.05
     puzzled
    1.02
     perplexing
    1.01
     WTF
    0.98
     wtf
    0.95
     unexplained
    0.95
    Act Density 0.373%

    No Known Activations