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

    Neuronpedia

    INDEX
    Explanations

    Code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Letters
    -0.07
    -0.07
     생산
    -0.06
    ="#"
    -0.06
    ollen
    -0.06
    ;'↵
    -0.06
    Production
    -0.06
    ratio
    -0.06
    _ACT
    -0.06
     також
    -0.06
    POSITIVE LOGITS
     View
    0.07
     RecognitionException
    0.07
     Sessions
    0.07
     bones
    0.06
     Gay
    0.06
     güc
    0.06
    idy
    0.06
     presenting
    0.06
     Nero
    0.06
     crank
    0.06
    Act Density 0.046%

    No Known Activations