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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions and reactions

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

    feelings or emotions

    np_acts-logits-general · gemini-2.0-flash

    expressions of strong emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -0.69
    filepath
    -0.63
    brigens
    -0.58
    Портали
    -0.56
     الدولى
    -0.54
     IActionResult
    -0.51
    migrationBuilder
    -0.49
     дописавши
    -0.48
    platform
    -0.48
     ویکی‌پدیای
    -0.48
    POSITIVE LOGITS
    ьаж
    0.69
     seeing
    0.69
     hearing
    0.65
     knowing
    0.59
     about
    0.59
     realizing
    0.59
     légitime
    0.59
     discovering
    0.57
    看到
    0.57
     powodu
    0.56
    Act Density 0.188%

    No Known Activations