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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     The
    -0.06
     and
    -0.06
     به
    -0.06
    **)&
    -0.06
     intercourse
    -0.06
     vedle
    -0.06
     In
    -0.06
     appealed
    -0.06
    Merit
    -0.06
    　　 　
    -0.06
    POSITIVE LOGITS
    `,
    0.08
    fic
    0.08
    ”,
    0.08
    UNG
    0.07
    lığa
    0.07
    ,’
    0.07
    ,max
    0.07
    ,
    0.07
    jm
    0.06
    ],
    0.06
    Act Density 2.926%

    No Known Activations