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

    Neuronpedia

    INDEX
    Explanations

    math questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Storage
    -0.07
     cake
    -0.07
     WHICH
    -0.07
    自己的
    -0.06
     *,
    -0.06
     nơi
    -0.06
     marketplace
    -0.06
    术
    -0.06
     tenure
    -0.06
    ception
    -0.06
    POSITIVE LOGITS
    REAT
    0.07
    Commerce
    0.06
    legant
    0.06
     indicates
    0.06
    \Action
    0.06
    (inner
    0.06
     Codes
    0.06
     Threat
    0.06
    Decimal
    0.06
    üy
    0.06
    Act Density 0.147%

    No Known Activations