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

    Neuronpedia

    INDEX
    Explanations

    correcting errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Barth
    -0.07
    .Script
    -0.07
    .lua
    -0.07
     Putting
    -0.06
     ثم
    -0.06
     upper
    -0.06
    /******/↵
    -0.06
     Cycle
    -0.06
     church
    -0.06
     Ribbon
    -0.06
    POSITIVE LOGITS
    Eq
    0.07
     TBD
    0.07
     преп
    0.07
    lili
    0.07
    権
    0.06
    ğinden
    0.06
    "),↵
    0.06
    eat
    0.06
    leave
    0.06
    '=>$
    0.06
    Act Density 0.016%

    No Known Activations