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

    Neuronpedia

    INDEX
    Explanations

    redundant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     habrá
    -0.09
    ��
    -0.08
    дание
    -0.08
    關
    -0.08
     scrambling
    -0.08
     delicios
    -0.08
     vien
    -0.08
     tiek
    -0.08
    稍
    -0.08
    iscipline
    -0.07
    POSITIVE LOGITS
     unnecessary
    0.11
     redundant
    0.11
     inutil
    0.11
     ઘટાડ
    0.10
     useless
    0.10
     తగ్గ
    0.10
     needless
    0.10
     inutile
    0.10
    Unused
    0.10
     removable
    0.09
    Act Density 0.007%

    No Known Activations