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

    Neuronpedia

    INDEX
    Explanations

    avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç»ĵ
    -0.28
    æĪijä¸įæĺ¯
    -0.27
    è¯ķéªĮåĮº
    -0.26
     preamble
    -0.25
    _pars
    -0.25
    waters
    -0.25
    çļĦèī¯å¥½
    -0.24
    oyer
    -0.24
    amespace
    -0.24
    Theory
    -0.23
    POSITIVE LOGITS
     Peace
    0.28
    elry
    0.27
     Bre
    0.26
    ÑĢе
    0.26
     correspond
    0.25
     peace
    0.25
    èĪŀ
    0.25
     Brave
    0.25
    haft
    0.24
    Usu
    0.24
    Act Density 0.876%

    No Known Activations