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

    Neuronpedia

    INDEX
    Explanations

    stabil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptive
    -0.28
    èľľ
    -0.28
    äºĮ级
    -0.26
    adow
    -0.26
    粪
    -0.25
    åľ¬
    -0.25
    ç»Īç»ĵ
    -0.25
    åݲ
    -0.25
    åıĺçİ°
    -0.24
    Checked
    -0.24
    POSITIVE LOGITS
     casualty
    0.31
    TRS
    0.26
     Kaiser
    0.26
    /TR
    0.25
    çļĦéĩį大
    0.25
     aesthetics
    0.25
    æŀī
    0.25
     commuting
    0.24
    makers
    0.24
    ARS
    0.24
    Act Density 0.001%

    No Known Activations