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

    Neuronpedia

    INDEX
    Explanations

    Ann Arbor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    has
    -0.07
     Juda
    -0.07
     xrange
    -0.07
    "])↵↵
    -0.07
     accomplishment
    -0.07
    forall
    -0.06
    [↵
    -0.06
     Gospel
    -0.06
    Smooth
    -0.06
     Ancient
    -0.06
    POSITIVE LOGITS
    พอ
    0.06
    连接
    0.06
    šil
    0.06
    定的
    0.06
     파
    0.06
    =A
    0.06
     konz
    0.06
    Ｂ
    0.06
     будут
    0.06
     همراه
    0.06
    Act Density 0.012%

    No Known Activations