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

    Neuronpedia

    INDEX
    Explanations

    flag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eval
    -0.07
     museums
    -0.07
     nave
    -0.06
    peace
    -0.06
    reff
    -0.06
     زمانی
    -0.06
     元
    -0.06
     DAM
    -0.06
     pare
    -0.06
    -fix
    -0.06
    POSITIVE LOGITS
    ѓ
    0.07
    شور
    0.07
    getline
    0.06
    AtIndex
    0.06
    令人
    0.06
     renters
    0.06
    andering
    0.06
     rw
    0.06
    انون
    0.06
    (robot
    0.06
    Act Density 0.001%

    No Known Activations