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

    Neuronpedia

    INDEX
    Explanations

    reported speech or quotations

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

    "said" followed by a name

    np_acts-logits-general · gemini-2.0-flash

    reporting verb said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.92
    ChildScrollView
    -0.87
    abestanden
    -0.83
     estekak
    -0.79
    `]
    -0.78
    '])->
    -0.76
     nahilalakip
    -0.74
    Crossref
    -0.74
    bibinfo
    -0.73
     MOP
    -0.72
    POSITIVE LOGITS
     nothing
    0.72
     goodbye
    0.70
     earlier
    0.56
    sak
    0.56
     NOTHING
    0.54
     no
    0.54
     yes
    0.53
     to
    0.52
     he
    0.52
     it
    0.51
    Act Density 0.047%

    No Known Activations