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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .unit
    -0.07
    clock
    -0.07
    249
    -0.07
    _dn
    -0.06
    issy
    -0.06
    loit
    -0.06
    ())
    -0.06
    Handled
    -0.06
    와
    -0.06
    Padding
    -0.06
    POSITIVE LOGITS
     intric
    0.06
     particip
    0.06
    )!
    0.06
     acknowled
    0.06
    bakan
    0.06
     přísluš
    0.06
     treatment
    0.06
     Verfügung
    0.06
     болезни
    0.06
     loot
    0.06
    Act Density 0.155%

    No Known Activations