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

    Neuronpedia

    INDEX
    Explanations

    bi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cast
    -0.07
    초
    -0.07
     أن
    -0.07
     проч
    -0.07
    命
    -0.07
    觉
    -0.07
    838
    -0.06
    Metal
    -0.06
    clamation
    -0.06
     Sr
    -0.06
    POSITIVE LOGITS
     bi
    0.09
    になり
    0.07
     ji
    0.06
     Bi
    0.06
     Во
    0.06
     bele
    0.06
     yearly
    0.06
    Plane
    0.06
     erotico
    0.06
    ованих
    0.06
    Act Density 0.005%

    No Known Activations