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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कब
    -0.07
     brakes
    -0.06
     Gab
    -0.06
    setUp
    -0.06
     حق
    -0.06
     HOME
    -0.06
     Isl
    -0.06
     req
    -0.06
     gab
    -0.06
    getName
    -0.06
    POSITIVE LOGITS
    >To
    0.08
    şam
    0.07
    —
    0.07
     skill
    0.07
    Only
    0.07
    Khi
    0.07
     To
    0.07
    ιών
    0.07
    cks
    0.07
     Μον
    0.06
    Act Density 0.014%

    No Known Activations