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

    Neuronpedia

    INDEX
    Explanations

    terms related to significance and utility in research contexts

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

    beneficial and important qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fotográfico
    -0.40
    dollis
    -0.39
    bibfield
    -0.39
     argint
    -0.38
    Rüyada
    -0.35
     estacion
    -0.35
    Biografi
    -0.34
     maș
    -0.33
    GEBURTSDATUM
    -0.33
     administrativo
    -0.32
    POSITIVE LOGITS
     especially
    0.67
    especially
    0.58
     particularly
    0.56
    Билгалдахарш
    0.54
    omitempty
    0.54
    CheckBreak
    0.52
    Especially
    0.52
     Especially
    0.50
    NotNil
    0.49
    autant
    0.49
    Act Density 0.070%

    No Known Activations