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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     card
    -0.07
     track
    -0.07
     memory
    -0.07
     myocard
    -0.07
     margin
    -0.07
     Matter
    -0.06
    56
    -0.06
    students
    -0.06
     GM
    -0.06
     VR
    -0.06
    POSITIVE LOGITS
    เ�
    0.07
     kamu
    0.07
     ön
    0.06
    .Millisecond
    0.06
    IRST
    0.06
     کاهش
    0.06
     앞
    0.06
    niž
    0.06
     heir
    0.06
    ѓ
    0.06
    Act Density 0.041%

    No Known Activations