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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    文章
    -0.07
    ems
    -0.07
     Maple
    -0.07
    ồi
    -0.07
     위해서
    -0.06
     następnie
    -0.06
    嗓子
    -0.06
    esthes
    -0.06
    (index
    -0.06
    abble
    -0.06
    POSITIVE LOGITS
     التابعة
    0.07
    صراع
    0.07
    덫
    0.07
     형태
    0.07
    Instruction
    0.07
    Framework
    0.07
     Mak
    0.07
    .pk
    0.07
    FieldName
    0.06
     deported
    0.06
    Act Density 0.001%

    No Known Activations