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

    Neuronpedia

    INDEX
    Explanations

    in this case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dare
    0.41
     Possibly
    0.40
    dbox
    0.39
    Possibly
    0.37
     Honestly
    0.37
     façon
    0.37
    以來
    0.36
    高
    0.36
    エスト
    0.36
    <0xA2>
    0.36
    POSITIVE LOGITS
     случа
    0.95
     przypadku
    0.94
     caso
    0.91
     cazul
    0.86
     경우
    0.84
     случае
    0.82
    กรณี
    0.80
     kasus
    0.79
     경우에는
    0.79
     випадку
    0.77
    Act Density 0.015%

    No Known Activations