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

    Neuronpedia

    INDEX
    Explanations

    self, thoughts, feelings, existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nagy
    0.33
    醃
    0.32
    يس
    0.31
     snippet
    0.30
     magic
    0.30
     sn
    0.29
    ymce
    0.29
    magic
    0.29
    ផ្
    0.29
     biraz
    0.29
    POSITIVE LOGITS
     personality
    0.59
     abilities
    0.53
     psyche
    0.51
     personalidad
    0.51
     individuality
    0.50
     personalidade
    0.50
     own
    0.50
     personalità
    0.48
     personnalité
    0.48
     physiology
    0.47
    Act Density 0.093%

    No Known Activations