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

    Neuronpedia

    INDEX
    Explanations

    Japanese words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जापान
    0.48
    lí
    0.44
     Jepang
    0.44
     Á
    0.43
     Ching
    0.43
    geç
    0.41
    淞
    0.41
     जो
    0.41
    वाडी
    0.41
    廁
    0.41
    POSITIVE LOGITS
    ari
    0.53
    ume
    0.50
    umo
    0.49
    ogi
    0.47
    urig
    0.47
    ome
    0.47
    ami
    0.46
    umi
    0.45
    emu
    0.44
    ere
    0.42
    Act Density 0.007%

    No Known Activations