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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cr
    -0.07
     tháng
    -0.06
     regs
    -0.06
     случ
    -0.06
     poate
    -0.06
    {};↵
    -0.06
     Witt
    -0.06
    ประก
    -0.06
     doub
    -0.06
     olmam
    -0.06
    POSITIVE LOGITS
    COPE
    0.07
    ΙΚΗ
    0.07
     catapult
    0.06
     improves
    0.06
     increased
    0.06
    oso
    0.06
    efe
    0.06
    ्फ
    0.06
    _System
    0.06
    %)
    0.06
    Act Density 0.051%

    No Known Activations