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

    Neuronpedia

    INDEX
    Explanations

    python, java, go imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🅷
    0.31
     douche
    0.30
     anore
    0.30
     अधी
    0.30
    ルフ
    0.30
    ᕝ
    0.30
     nourriture
    0.29
     svij
    0.29
     specialises
    0.29
    Samantha
    0.29
    POSITIVE LOGITS
     M
    0.32
     Uniform
    0.29
     Cel
    0.27
     C
    0.27
     Win
    0.26
     Progressive
    0.26
     dia
    0.26
     Dia
    0.26
     Ded
    0.25
     D
    0.25
    Act Density 0.006%

    No Known Activations