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

    Neuronpedia

    INDEX
    Explanations

    problems, specific domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     näher
    0.41
     aktual
    0.41
     keiner
    0.40
     mehrerer
    0.40
    Subsequently
    0.39
     மதிப்ப
    0.38
     Haunted
    0.38
     lud
    0.38
     之
    0.38
     verstehen
    0.38
    POSITIVE LOGITS
    ם
    0.46
    ັດ
    0.44
     partnering
    0.41
    pregnancy
    0.40
    Android
    0.40
    the
    0.38
     magari
    0.38
     piano
    0.38
     unreliable
    0.38
     personel
    0.38
    Act Density 0.000%

    No Known Activations