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

    Neuronpedia

    INDEX
    Explanations

    security and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Europa
    0.44
     своими
    0.43
    ruv
    0.43
    et
    0.42
    london
    0.41
    imit
    0.41
    moon
    0.40
    ie
    0.40
     Europa
    0.40
    ding
    0.40
    POSITIVE LOGITS
    하여
    0.47
     của
    0.46
    さて
    0.46
    觀塘
    0.45
     realidade
    0.44
     siglas
    0.44
    actory
    0.43
    <?
    0.43
    在
    0.43
     του
    0.43
    Act Density 0.002%

    No Known Activations