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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	pid
    -0.07
     Crushers
    -0.07
    Unsafe
    -0.06
    .longitude
    -0.06
    authorization
    -0.06
    Hyper
    -0.06
     obligation
    -0.06
     creations
    -0.06
    [root
    -0.06
    _activ
    -0.06
    POSITIVE LOGITS
     мо
    0.07
    ="<?
    0.06
    _qu
    0.06
    SPEC
    0.06
    ',↵↵
    0.06
    B
    0.06
    dü
    0.06
     připoj
    0.06
     NEXT
    0.06
     viol
    0.06
    Act Density 0.009%

    No Known Activations