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

    Neuronpedia

    INDEX
    Explanations

    examples like these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যখন
    0.43
    ться
    0.41
     edema
    0.41
     অবশেষে
    0.41
     productor
    0.41
    пти
    0.40
     slipping
    0.40
     gasoline
    0.40
    си
    0.39
    にて
    0.38
    POSITIVE LOGITS
     ϒ
    0.47
    誅
    0.47
    悹
    0.46
     果
    0.45
    volumes
    0.45
    埧
    0.45
     BYU
    0.44
    䄳
    0.44
     श्रद्धा
    0.43
    ϒ
    0.43
    Act Density 0.001%

    No Known Activations