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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beispiel
    -0.07
     maxim
    -0.07
     код
    -0.07
     kube
    -0.06
    _OD
    -0.06
     Xm
    -0.06
     TERMIN
    -0.06
    ��
    -0.06
    antino
    -0.06
    Chr
    -0.06
    POSITIVE LOGITS
    цик
    0.06
     requisite
    0.06
    -tax
    0.06
     cracking
    0.06
     branching
    0.06
    -anchor
    0.06
     编辑
    0.06
     slashing
    0.06
     snatch
    0.06
     reverted
    0.06
    Act Density 0.197%

    No Known Activations