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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibble
    -0.06
    ze
    -0.06
     yanlış
    -0.06
     tả
    -0.06
     Watts
    -0.06
     neut
    -0.06
    亜
    -0.06
     imag
    -0.06
    dj
    -0.06
    Perfect
    -0.06
    POSITIVE LOGITS
     secrecy
    0.07
    ."[
    0.07
     legacy
    0.06
    ='".$
    0.06
     patches
    0.06
     θ
    0.06
     startX
    0.06
    )[:
    0.06
    _TYPE
    0.06
     {{--
    0.06
    Act Density 0.002%

    No Known Activations