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

    Neuronpedia

    INDEX
    Explanations

    debugging or tracing commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imperative
    -0.09
     oferecer
    -0.09
     incentivar
    -0.09
    기에
    -0.08
     ذك
    -0.08
     shutter
    -0.08
    措施
    -0.07
     ofrecer
    -0.07
     مي
    -0.07
     recordar
    -0.07
    POSITIVE LOGITS
     failing
    0.11
     workings
    0.09
    failed
    0.09
    fail
    0.09
    Failed
    0.08
    .alloc
    0.08
    .debug
    0.08
    	fail
    0.08
    FAIL
    0.08
    Alloc
    0.08
    Act Density 0.009%

    No Known Activations