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

    Neuronpedia

    INDEX
    Explanations

    abstract nouns and concepts related to evaluation and classification

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

    qualities and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.55
     vVar
    -0.54
    ihnach
    -0.54
     ProtoMessage
    -0.53
    Gön
    -0.52
    erintah
    -0.49
     незавершена
    -0.49
     laſſen
    -0.48
     EClass
    -0.48
    enschappe
    -0.48
    POSITIVE LOGITS
    0.48
     bäst
    0.41
     psicológica
    0.37
     afectadas
    0.35
     qualidade
    0.34
     puissance
    0.33
    calipsis
    0.33
     qualité
    0.33
     constitucional
    0.33
     colombiana
    0.33
    Act Density 0.458%

    No Known Activations