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

    Neuronpedia

    INDEX
    Explanations

    methods or processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    holes
    -0.28
     Cond
    -0.27
    /part
    -0.27
    kim
    -0.26
    /Resources
    -0.25
    éªIJ
    -0.25
     physiology
    -0.25
    è·Ľ
    -0.25
    éĢ»
    -0.24
    inson
    -0.24
    POSITIVE LOGITS
    æĮī
    0.31
    表示
    0.27
     passing
    0.27
     weighted
    0.27
    称
    0.26
     <![
    0.26
    6
    0.25
    ç¬Ķ
    0.25
    贯穿
    0.25
    å¸ħ
    0.25
    Act Density 0.071%

    No Known Activations