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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terminals
    -0.07
     arist
    -0.07
    (stypy
    -0.06
     вход
    -0.06
    hour
    -0.06
    /repository
    -0.06
     microseconds
    -0.06
     "=
    -0.06
    _fre
    -0.06
     TRI
    -0.06
    POSITIVE LOGITS
    Interpreter
    0.07
     Techniques
    0.07
    арч
    0.06
    _label
    0.06
     Nicolas
    0.06
     Libya
    0.06
    ệnh
    0.06
     تحصیل
    0.06
     intellectually
    0.06
    (ctx
    0.06
    Act Density 0.048%

    No Known Activations