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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فل
    -0.07
    ětš
    -0.07
    cky
    -0.07
    스터
    -0.06
    offee
    -0.06
    _compiler
    -0.06
    eného
    -0.06
     Luke
    -0.06
     minimal
    -0.06
    이나
    -0.06
    POSITIVE LOGITS
    .SizeF
    0.07
    사항
    0.06
     getPassword
    0.06
     Obst
    0.06
    ологии
    0.06
     Cologne
    0.06
     avail
    0.06
     vzdál
    0.06
     allocate
    0.06
     assert
    0.06
    Act Density 0.016%

    No Known Activations