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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifax
    -0.07
    esiyle
    -0.06
     раздел
    -0.06
     Live
    -0.06
     것이
    -0.06
    ']").
    -0.06
    rové
    -0.06
    rvine
    -0.06
    ведите
    -0.06
     Deer
    -0.05
    POSITIVE LOGITS
     implication
    0.07
    apply
    0.07
    ，是
    0.07
    /window
    0.07
    parameter
    0.07
     DIFF
    0.07
    -axis
    0.06
     llama
    0.06
    <input
    0.06
    _HELP
    0.06
    Act Density 0.005%

    No Known Activations