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

    Neuronpedia

    INDEX
    Explanations

    to/not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pNode
    -0.07
     FALL
    -0.07
    _valor
    -0.06
     fuzz
    -0.06
    н
    -0.06
    ,ID
    -0.06
     sürec
    -0.06
     cree
    -0.06
     Öğ
    -0.06
     WL
    -0.06
    POSITIVE LOGITS
    _ASSUME
    0.08
    AMY
    0.07
    enses
    0.06
    ucz
    0.06
    .reject
    0.06
     Sie
    0.06
    ="${
    0.06
     بعدی
    0.06
    839
    0.06
    ">${
    0.06
    Act Density 0.014%

    No Known Activations