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

    Neuronpedia

    INDEX
    Explanations

    code/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ków
    -0.07
    ��
    -0.06
    птом
    -0.06
    ch
    -0.06
     Sponsored
    -0.06
    ентами
    -0.06
    様
    -0.06
    axios
    -0.06
     był
    -0.06
     управління
    -0.06
    POSITIVE LOGITS
    atsby
    0.07
    .AR
    0.07
    ,t
    0.07
     menu
    0.07
     код
    0.07
     cort
    0.06
    ี.
    0.06
    awei
    0.06
    ทร
    0.06
    dismiss
    0.06
    Act Density 0.000%

    No Known Activations