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

    Neuronpedia

    INDEX
    Explanations

    algorithm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dancer
    -0.07
     amendment
    -0.07
     distortion
    -0.07
     Toilet
    -0.07
     mighty
    -0.06
    Parents
    -0.06
    legates
    -0.06
     diplomats
    -0.06
    صور
    -0.06
     bm
    -0.06
    POSITIVE LOGITS
     şans
    0.07
     Lei
    0.07
     白
    0.06
    ]))
↵
    0.06
    ейчас
    0.06
     Mog
    0.06
    Tensor
    0.06
     政
    0.06
     카지노
    0.06
    Pay
    0.06
    Act Density 0.012%

    No Known Activations