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

    Neuronpedia

    INDEX
    Explanations

    genetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     får
    -0.07
    masından
    -0.06
     defa
    -0.06
    ушки
    -0.06
     dokon
    -0.06
     Finnish
    -0.06
     Πρό
    -0.06
     отк
    -0.06
     Ahead
    -0.06
     findBy
    -0.06
    POSITIVE LOGITS
     Russ
    0.06
    ,string
    0.06
    μερα
    0.06
    XT
    0.06
    Inst
    0.06
     Charlotte
    0.06
    hips
    0.06
    stud
    0.06
     rational
    0.06
     Lose
    0.06
    Act Density 0.000%

    No Known Activations