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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upkeep
    -0.07
     hect
    -0.06
     भगव
    -0.06
     Praha
    -0.06
     also
    -0.06
     capture
    -0.06
     sanct
    -0.06
     plight
    -0.06
     např
    -0.06
     پي
    -0.06
    POSITIVE LOGITS
    imli
    0.07
    //[
    0.06
     간
    0.06
     усіх
    0.06
     biliyor
    0.06
    ุด
    0.06
    εί
    0.06
    DN
    0.06
    Rand
    0.06
     DUP
    0.06
    Act Density 0.005%

    No Known Activations