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

    Neuronpedia

    INDEX
    Explanations

    offered offered provided used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ани
    0.46
     коли
    0.44
    Localized
    0.42
    িনিয়ার
    0.41
    Anything
    0.40
    ляр
    0.39
    嫘
    0.39
     Qualquer
    0.39
     anything
    0.38
    Quando
    0.38
    POSITIVE LOGITS
     сейчас
    0.41
    私が
    0.40
     지금
    0.38
    今天
    0.37
     proposed
    0.37
     offered
    0.37
     мной
    0.36
     सामने
    0.36
     ký
    0.36
     used
    0.35
    Act Density 0.124%

    No Known Activations