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
    .getMin
    -0.07
    City
    -0.06
     Peng
    -0.06
     fputs
    -0.06
     quasi
    -0.06
     Ronaldo
    -0.06
     countertops
    -0.06
     fopen
    -0.06
    怪
    -0.06
     snapshot
    -0.06
    POSITIVE LOGITS
    ژه
    0.07
     жит
    0.07
    verige
    0.07
    ικοί
    0.07
     hvis
    0.07
     Deutschland
    0.06
    [arg
    0.06
     переш
    0.06
    (step
    0.06
     ох
    0.06
    Act Density 0.065%

    No Known Activations