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

    Neuronpedia

    INDEX
    Explanations

    price, example, becomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    วรร
    0.46
     accomplishments
    0.40
    \#
    0.39
    角落
    0.38
     przyczyn
    0.37
    ㄚ
    0.37
     taw
    0.37
     gird
    0.36
     parasitic
    0.36
     SCGS
    0.36
    POSITIVE LOGITS
     იქნება
    0.42
     цена
    0.41
    であれば
    0.40
     डेढ़
    0.39
     देखील
    0.39
     masy
    0.37
     எத்தனை
    0.37
    ాలంటే
    0.37
    दूसरे
    0.36
     وحده
    0.36
    Act Density 0.001%

    No Known Activations