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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    placeholders
    -0.06
    油
    -0.06
     policing
    -0.06
    .setOutput
    -0.06
    rock
    -0.06
     Butt
    -0.06
    openh
    -0.06
    Handling
    -0.06
     Late
    -0.06
    shapes
    -0.06
    POSITIVE LOGITS
     grinned
    0.07
    -section
    0.07
    129
    0.07
     ein
    0.07
     prevented
    0.06
    /interfaces
    0.06
    	emit
    0.06
     landed
    0.06
    iphers
    0.06
     barred
    0.06
    Act Density 0.002%

    No Known Activations