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

    Neuronpedia

    INDEX
    Explanations

    aw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帮åĬ©ä¼ģä¸ļ
    -0.30
    çļĦéľĢæ±Ĥ
    -0.27
    çļĦ帮åĬ©
    -0.26
    ä¾Ľæ±Ĥ
    -0.26
    æŃ¢
    -0.25
     desires
    -0.25
    ä¾ĽéľĢ
    -0.25
     beliefs
    -0.25
    èĤĺ
    -0.24
     resisted
    -0.24
    POSITIVE LOGITS
    allon
    0.27
    affer
    0.26
    sth
    0.26
    ancia
    0.25
    .arc
    0.25
    æīģ
    0.24
    æıIJåıĸ
    0.24
    etz
    0.23
    blick
    0.23
    ãģĵãģĿ
    0.23
    Act Density 0.078%

    No Known Activations