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

    Neuronpedia

    INDEX
    Explanations

    orthonormal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .idx
    -0.07
    ปล
    -0.07
    应急
    -0.07
     Cost
    -0.07
    )-
    -0.07
    .vx
    -0.06
    cycle
    -0.06
    心疼
    -0.06
    경
    -0.06
     Opt
    -0.06
    POSITIVE LOGITS
     AK
    0.08
     заявил
    0.08
    NJ
    0.07
    巨头
    0.07
    Ģ
    0.07
    (fabs
    0.07
     Sav
    0.07
    .SetValue
    0.07
     NVIDIA
    0.07
    Β
    0.07
    Act Density 0.002%

    No Known Activations