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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hrs
    -0.07
     й
    -0.07
    mit
    -0.06
     RC
    -0.06
     bold
    -0.06
     виробництва
    -0.06
     sigma
    -0.06
     Fry
    -0.06
    _copy
    -0.06
     materiál
    -0.06
    POSITIVE LOGITS
     weekday
    0.07
    ولي
    0.07
     outnumber
    0.07
    SpecWarn
    0.07
    	glm
    0.07
    .gradle
    0.06
    =edge
    0.06
    NSData
    0.06
    anced
    0.06
    iste
    0.06
    Act Density 0.013%

    No Known Activations