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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urine
    -0.08
    Indexes
    -0.07
     Foam
    -0.07
     España
    -0.06
    蓝
    -0.06
    erv
    -0.06
     dew
    -0.06
    の上
    -0.06
     LABEL
    -0.06
    眼睛
    -0.06
    POSITIVE LOGITS
     tenure
    0.07
     chord
    0.07
    RAR
    0.06
     camb
    0.06
     rpm
    0.06
     spur
    0.06
    931
    0.06
    mise
    0.06
     направ
    0.06
    同步
    0.05
    Act Density 0.310%

    No Known Activations