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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chg
    -0.07
    .mipmap
    -0.06
    /em
    -0.06
    _CNTL
    -0.06
    >;
    -0.06
    #↵↵
    -0.06
     unins
    -0.06
    />.
    -0.06
    erras
    -0.06
     Γεω
    -0.06
    POSITIVE LOGITS
     bbc
    0.07
    LI
    0.06
    lier
    0.06
     reck
    0.06
     WWW
    0.06
    lic
    0.06
     dood
    0.06
     ply
    0.06
     besoin
    0.06
     순간
    0.06
    Act Density 0.019%

    No Known Activations