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

    Neuronpedia

    INDEX
    Explanations

    instances of quotes or direct speech

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

    solve math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.71
    Personendaten
    -0.69
    Tikang
    -0.67
    хьтан
    -0.64
     autorytatywna
    -0.60
     faſt
    -0.60
     Comprometido
    -0.58
    adpleegd
    -0.57
    parsedMessage
    -0.57
     OMITBAD
    -0.55
    POSITIVE LOGITS
    The
    0.38
    FragmentManager
    0.34
     recently
    0.34
    ManyToOne
    0.34
     recenti
    0.34
    риф
    0.32
    recently
    0.32
    EMBLE
    0.32
    ậm
    0.31
     編集
    0.31
    Act Density 0.037%

    No Known Activations