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

    Neuronpedia

    INDEX
    Explanations

    bordering countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    0.63
    е
    0.58
    ে
    0.54
    ي
    0.54
     דר
    0.51
     מ
    0.49
     מר
    0.48
     కొంత
    0.48
     التن
    0.47
     dwRes
    0.47
    POSITIVE LOGITS
    CK
    0.51
     speaking
    0.44
     leuke
    0.43
    ॉकलेट
    0.43
     penampilan
    0.43
    Britain
    0.42
    Mik
    0.42
    uance
    0.42
    一つ
    0.42
    GAM
    0.42
    Act Density 0.000%

    No Known Activations