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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ве
    -0.07
     pos
    -0.07
     sunshine
    -0.06
     Dat
    -0.06
     sábado
    -0.06
    (bar
    -0.06
     Böyle
    -0.06
    Notification
    -0.06
    entarios
    -0.06
     écrit
    -0.06
    POSITIVE LOGITS
    512
    0.07
     derin
    0.06
    truncate
    0.06
     Beyond
    0.06
    ϊ
    0.06
    _ATTR
    0.06
     Club
    0.06
    عن
    0.06
    resi
    0.06
    heat
    0.06
    Act Density 0.001%

    No Known Activations