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

    Neuronpedia

    INDEX
    Explanations

    printing or logging results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    граф
    0.40
     catalytic
    0.38
     habitat
    0.38
    拋
    0.37
    ettes
    0.36
     cannabin
    0.35
     করিয়
    0.35
    \{(
    0.35
     actuators
    0.35
     촬영
    0.35
    POSITIVE LOGITS
    empty
    0.59
    even
    0.52
     empty
    0.52
     빈
    0.50
    Empty
    0.48
     Empty
    0.48
     sogar
    0.48
     even
    0.48
     invalid
    0.47
     negatif
    0.47
    Act Density 0.016%

    No Known Activations