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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anderen
    -0.08
     Trap
    -0.07
    :y
    -0.06
     Banana
    -0.06
     rotary
    -0.06
    _neg
    -0.06
    _reverse
    -0.06
     tutors
    -0.06
    _Surface
    -0.06
    aked
    -0.06
    POSITIVE LOGITS
    world
    0.08
            	↵
    0.06
    =forms
    0.06
    (Thread
    0.06
    	re
    0.06
    thy
    0.06
    ์ได
    0.06
     TD
    0.06
    ايا
    0.06
    、二
    0.06
    Act Density 0.048%

    No Known Activations