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

    Neuronpedia

    INDEX
    Explanations

    self and identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    气氛
    0.85
    ให้บริการ
    0.80
     isothermal
    0.79
     malware
    0.76
     prosedur
    0.74
     procédures
    0.72
     종료
    0.72
     hyperlink
    0.70
     IOException
    0.69
     தொற்று
    0.68
    POSITIVE LOGITS
     self
    1.78
     Self
    1.68
    Self
    1.67
     identity
    1.67
    自我
    1.60
     identidad
    1.56
    Identity
    1.53
    self
    1.50
    identity
    1.49
     SELF
    1.49
    Act Density 0.739%

    No Known Activations