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

    Neuronpedia

    INDEX
    Explanations

    start of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfermedad
    -0.08
     genel
    -0.07
     उसका
    -0.07
     ऐसा
    -0.07
     있다는
    -0.07
     wasting
    -0.07
     있다
    -0.07
     ਹਾਂ
    -0.07
     మధ్య
    -0.07
    .no
    -0.07
    POSITIVE LOGITS
    原
    0.10
     originale
    0.10
     ursprünglich
    0.10
    .original
    0.10
    original
    0.10
     intended
    0.10
     原
    0.10
    iginal
    0.09
     intenção
    0.09
     untouched
    0.09
    Act Density 0.072%

    No Known Activations