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

    Neuronpedia

    INDEX
    Explanations

    city names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itten
    -0.07
     TOP
    -0.07
    ْف
    -0.06
    λώ
    -0.06
     CRT
    -0.06
    Ford
    -0.06
     RENDER
    -0.06
    υμ
    -0.06
     Cad
    -0.06
    icemail
    -0.06
    POSITIVE LOGITS
    .tasks
    0.07
    .velocity
    0.06
    νου
    0.06
    (g
    0.06
     valores
    0.06
     Partial
    0.06
     fate
    0.06
    _title
    0.06
     coords
    0.06
    02
    0.06
    Act Density 0.009%

    No Known Activations