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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (patient
    -0.07
     equivalents
    -0.07
     gì
    -0.06
     Idaho
    -0.06
     insured
    -0.06
     rhs
    -0.06
    _TV
    -0.06
     jaký
    -0.06
     improves
    -0.06
     blízk
    -0.06
    POSITIVE LOGITS
     Eight
    0.07
     �
    0.06
    .Conv
    0.06
    ตรว
    0.06
    613
    0.06
    ,
↵
↵
    0.06
     **************************************************************************
    0.06
    plat
    0.06
    kerja
    0.06
    기는
    0.06
    Act Density 0.037%

    No Known Activations