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

    Neuronpedia

    INDEX
    Explanations

    possible/impossible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parking
    -0.06
     dungeon
    -0.06
    ARD
    -0.06
    azaar
    -0.06
    .base
    -0.06
    _REGION
    -0.06
    Wie
    -0.06
    pletely
    -0.06
     trebuie
    -0.06
    (extension
    -0.06
    POSITIVE LOGITS
     accidentally
    0.06
     jd
    0.06
    学生
    0.06
     žalob
    0.06
    ()){
    0.06
    (al
    0.06
    fds
    0.06
    .content
    0.06
    Incorrect
    0.06
     shy
    0.06
    Act Density 0.062%

    No Known Activations