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

    Neuronpedia

    INDEX
    Explanations

    non-latin scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ope
    0.40
     doves
    0.40
     showings
    0.40
     crackers
    0.39
     treasurer
    0.38
     polymerase
    0.38
     utterances
    0.38
     epoxide
    0.38
    clearRect
    0.38
     pep
    0.37
    POSITIVE LOGITS
    ند
    0.51
    қы
    0.50
    і
    0.49
    藉
    0.47
    İ
    0.47
    体验
    0.47
    زد
    0.46
    ක්‍
    0.46
    ก
    0.45
    સ્
    0.44
    Act Density 0.000%

    No Known Activations