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

    Neuronpedia

    INDEX
    Explanations

    citation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     studied
    -0.07
    _study
    -0.07
    DIST
    -0.07
    이라고
    -0.06
    verage
    -0.06
    �
    -0.06
     Arduino
    -0.06
     appending
    -0.06
     bouncing
    -0.06
    duino
    -0.06
    POSITIVE LOGITS
     tôi
    0.06
    addAction
    0.06
    urer
    0.06
     crew
    0.06
    ória
    0.06
     dur
    0.06
     strateg
    0.06
    ання
    0.06
     COVID
    0.06
     разі
    0.06
    Act Density 0.015%

    No Known Activations