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

    Neuronpedia

    INDEX
    Explanations

    bif

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exchanged
    -0.08
    Trail
    -0.07
    useum
    -0.07
     PACK
    -0.07
     Irene
    -0.06
    urple
    -0.06
    سمة
    -0.06
     blockDim
    -0.06
    commerce
    -0.06
    ')->
    -0.06
    POSITIVE LOGITS
     England
    0.06
     вообще
    0.06
    Một
    0.06
     считается
    0.06
    ５
    0.06
    .ContextCompat
    0.06
    cribes
    0.06
    े�
    0.06
    なの
    0.06
     الشي
    0.06
    Act Density 0.001%

    No Known Activations