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

    Neuronpedia

    INDEX
    Explanations

    decisions and actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kerr
    -0.07
     distress
    -0.07
     cro
    -0.07
     Área
    -0.07
     spe
    -0.07
     offene
    -0.07
     वै
    -0.07
     Ush
    -0.07
     humane
    -0.07
     flour
    -0.07
    POSITIVE LOGITS
     وكيف
    0.09
    Aval
    0.08
    ，以及
    0.08
    /generated
    0.08
     والتي
    0.08
    /connect
    0.08
     ਸੋ
    0.08
     nel
    0.08
    /look
    0.08
    เมื่อ
    0.08
    Act Density 0.275%

    No Known Activations