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

    Neuronpedia

    INDEX
    Explanations

    No longer/not acceptable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     starts
    -0.07
     begins
    -0.07
     Shortly
    -0.06
    	re
    -0.06
    Creat
    -0.06
    requested
    -0.06
     morale
    -0.06
    Axes
    -0.06
     far
    -0.06
    SSION
    -0.06
    POSITIVE LOGITS
    onna
    0.07
    brahim
    0.07
    면적
    0.07
    ические
    0.07
    lesh
    0.06
    ik
    0.06
     kalp
    0.06
    очных
    0.06
     عباس
    0.06
     devlet
    0.06
    Act Density 0.025%

    No Known Activations