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

    Neuronpedia

    INDEX
    Explanations

    distinguish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Iterator
    -0.09
    _ITER
    -0.09
    .iter
    -0.08
    ="%
    -0.08
     effet
    -0.08
    .Iter
    -0.08
     Starg
    -0.08
     Seren
    -0.08
     iterative
    -0.08
    (iter
    -0.08
    POSITIVE LOGITS
     distinction
    0.18
     onderscheid
    0.16
     distinguishing
    0.16
     distinguish
    0.15
     distinctions
    0.15
     distinguishes
    0.15
     distinguir
    0.14
     distingu
    0.14
     distin
    0.14
    区别
    0.14
    Act Density 0.043%

    No Known Activations