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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     послед
    -0.06
    无
    -0.06
     emulate
    -0.06
    utar
    -0.06
     delay
    -0.06
     through
    -0.06
     Definition
    -0.06
     olma
    -0.06
    ・・
    -0.06
     beware
    -0.06
    POSITIVE LOGITS
    ml
    0.07
    slides
    0.07
    rored
    0.07
     sizing
    0.06
     elgg
    0.06
    ặng
    0.06
    kemiz
    0.06
    �
    0.06
    /power
    0.06
     Norfolk
    0.06
    Act Density 0.000%

    No Known Activations