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

    Neuronpedia

    INDEX
    Explanations

    constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Meridian
    -0.09
     ڪمپ
    -0.08
     Medizin
    -0.08
     ويح
    -0.08
    વાનો
    -0.08
    Quaternion
    -0.08
    _empresa
    -0.08
    cklenburg
    -0.08
     나는
    -0.08
     পাক
    -0.08
    POSITIVE LOGITS
     maximizing
    0.11
     balancing
    0.11
     constraints
    0.11
     allocation
    0.10
     constraint
    0.10
     minimum
    0.10
     allocated
    0.10
     unavoidable
    0.09
    ≥
    0.09
    balance
    0.09
    Act Density 0.041%

    No Known Activations