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

    Neuronpedia

    INDEX
    Explanations

    language and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    拖
    0.41
     поста
    0.38
    ান্স
    0.38
    畕
    0.38
     leta
    0.37
    RAY
    0.37
    胃
    0.37
    顷
    0.36
    軸
    0.36
     기다
    0.36
    POSITIVE LOGITS
     Korean
    0.48
    various
    0.46
    inding
    0.44
    ological
    0.43
     કારણે
    0.42
     Signific
    0.42
    ffect
    0.41
     różne
    0.41
    th
    0.41
     Communication
    0.40
    Act Density 0.000%

    No Known Activations