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

    Neuronpedia

    INDEX
    Explanations

    particular context and its influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    根據
    0.46
    崠
    0.46
    㶱
    0.45
    㠱
    0.45
     KIT
    0.44
     merging
    0.43
     Trick
    0.42
     of
    0.42
    ัญลักษณ์
    0.42
    炔
    0.42
    POSITIVE LOGITS
    +.
    0.48
    ponses
    0.47
     seedlings
    0.46
    aków
    0.45
    anez
    0.45
    idders
    0.45
     नाखूनों
    0.44
    ल्फ़
    0.44
    বাহিনী
    0.44
    atan
    0.43
    Act Density 0.000%

    No Known Activations