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

    Neuronpedia

    INDEX
    Explanations

    chag, aggy, ogg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ভিল
    0.42
    Props
    0.40
    Referee
    0.40
    וחות
    0.40
    DEST
    0.39
     undue
    0.39
    ））
    0.38
    Expect
    0.36
    ლებ
    0.36
    Timeout
    0.36
    POSITIVE LOGITS
     ス
    0.40
    CharCode
    0.39
    اسية
    0.38
     Carp
    0.37
     babys
    0.37
    cosity
    0.36
     Malang
    0.36
     Stock
    0.35
     Carpet
    0.35
     customary
    0.35
    Act Density 0.000%

    No Known Activations