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

    Neuronpedia

    INDEX
    Explanations

    math and logic problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ptr
    -0.07
    .cloudflare
    -0.07
     أمر
    -0.06
     condemnation
    -0.06
    -Russian
    -0.06
    贫
    -0.06
    _FL
    -0.06
     ALS
    -0.06
     dlouhodob
    -0.06
     WHICH
    -0.06
    POSITIVE LOGITS
     mimetype
    0.07
     formulas
    0.07
     somewhere
    0.07
    orean
    0.07
     mí
    0.07
     tek
    0.07
    .pen
    0.06
     wisdom
    0.06
     peripheral
    0.06
     equation
    0.06
    Act Density 0.004%

    No Known Activations