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

    Neuronpedia

    INDEX
    Explanations

    to [number]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असं
    0.54
    บ่ง
    0.46
    iation
    0.45
    מיד
    0.45
    および
    0.44
     특정
    0.44
     ошибка
    0.43
     후
    0.43
    ired
    0.42
     डिज़ाइन
    0.42
    POSITIVE LOGITS
     Hulu
    0.48
     Europas
    0.45
     Ukraina
    0.44
     colonia
    0.43
     divent
    0.43
     Spotify
    0.41
     palt
    0.41
     loro
    0.41
     Gespr
    0.39
     HBO
    0.39
    Act Density 0.013%

    No Known Activations