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

    Neuronpedia

    INDEX
    Explanations

    check

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    167
    -0.07
     habitat
    -0.07
    aos
    -0.06
     đôi
    -0.06
     oblasti
    -0.06
     Rome
    -0.06
    rane
    -0.06
     устройства
    -0.06
     галуз
    -0.06
     sám
    -0.06
    POSITIVE LOGITS
    Check
    0.10
    .check
    0.10
    check
    0.10
     checks
    0.09
    CHECK
    0.09
     Check
    0.09
    _CHECK
    0.09
     CHECK
    0.09
     check
    0.09
    	Check
    0.08
    Act Density 0.018%

    No Known Activations