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

    Neuronpedia

    INDEX
    Explanations

    references to unspecified or vague subjects or objects

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

    "something"

    np_acts-logits-general · gemini-2.0-flash

    unspecified things and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Füßen
    -0.51
     oídos
    -0.51
     především
    -0.46
    Portály
    -0.46
     keuangan
    -0.45
     aikana
    -0.45
     prijzen
    -0.45
     miroir
    -0.43
     finanzas
    -0.43
     rač
    -0.43
    POSITIVE LOGITS
     something
    1.10
    Something
    1.06
     somethin
    1.04
     SOMETHING
    1.01
     Something
    1.01
     someone
    0.98
    someone
    0.97
    something
    0.97
    Someone
    0.94
    Somebody
    0.91
    Act Density 0.055%

    No Known Activations