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

    Neuronpedia

    INDEX
    Explanations

    unlimited quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    很多的
    0.49
     这些
    0.49
     directories
    0.46
    <unused78>
    0.45
     όλ
    0.45
     നടപ
    0.45
    実績
    0.44
    databases
    0.44
    很多
    0.44
    streets
    0.44
    POSITIVE LOGITS
     Walther
    0.41
     may
    0.41
     a
    0.40
    ციის
    0.40
     For
    0.40
    aire
    0.40
     Für
    0.40
    ెండు
    0.40
    製の
    0.40
     wound
    0.39
    Act Density 0.009%

    No Known Activations