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
     PL
    -0.06
    Apps
    -0.06
    graded
    -0.06
    programming
    -0.06
    (Cl
    -0.06
    руп
    -0.06
    _)
    -0.06
     budouc
    -0.06
    lict
    -0.06
     Stap
    -0.06
    POSITIVE LOGITS
    creativecommons
    0.08
    оці
    0.07
     visiting
    0.07
     ICU
    0.07
     حي
    0.06
    unately
    0.06
    هوری
    0.06
     Buy
    0.06
     И
    0.06
     sake
    0.06
    Act Density 0.000%

    No Known Activations