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

    Neuronpedia

    INDEX
    Explanations

    re looking, are doing, be buying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overrated
    0.35
    ampler
    0.35
    verm
    0.35
    Pregnant
    0.35
    ilm
    0.35
     வா
    0.34
     experienced
    0.34
     SAMSUNG
    0.34
     ყ
    0.33
     rated
    0.33
    POSITIVE LOGITS
    偎
    0.39
    碁
    0.39
    စာ
    0.37
    ฿
    0.36
    魎
    0.36
     Seitz
    0.36
     complexities
    0.36
    akta
    0.35
    ாலை
    0.35
    िष्ट
    0.35
    Act Density 0.212%

    No Known Activations