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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jan
    -0.07
     kn
    -0.07
     Rat
    -0.07
    Jan
    -0.07
    No
    -0.07
    Don
    -0.07
    499
    -0.07
     sort
    -0.07
    191
    -0.06
     Mant
    -0.06
    POSITIVE LOGITS
    0.08
    irie
    0.08
    0.08
    egie
    0.08
    0.08
    ece
    0.08
    emie
    0.08
    ریه
    0.08
     Peace
    0.08
    0.08
    Act Density 0.510%

    No Known Activations