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

    Neuronpedia

    INDEX
    Explanations

    model multilingual translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cast
    0.38
     costar
    0.38
    uetooth
    0.37
    ویزی
    0.36
     あの
    0.36
    侣
    0.36
    铜
    0.36
     ape
    0.35
     hydrostatic
    0.35
    igslist
    0.35
    POSITIVE LOGITS
     translated
    0.49
    translated
    0.49
    transl
    0.46
    Translation
    0.46
     Transl
    0.46
    Translated
    0.44
     Translation
    0.44
    translation
    0.43
     Translated
    0.42
    翻訳
    0.42
    Act Density 0.001%

    No Known Activations