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

    Neuronpedia

    INDEX
    Explanations

    closed-source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಹಿಂದ
    0.43
     Ae
    0.40
    Ae
    0.40
     CLP
    0.39
     Hint
    0.37
     Mauricio
    0.37
     Martín
    0.37
     Neur
    0.36
     Re
    0.36
     Adele
    0.36
    POSITIVE LOGITS
     proprietary
    0.45
    propri
    0.44
     propi
    0.43
     propriet
    0.40
    ͖
    0.38
     benz
    0.38
    丙基
    0.37
     எடுக்க
    0.37
     dik
    0.36
     Rais
    0.36
    Act Density 0.007%

    No Known Activations