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

    Neuronpedia

    INDEX
    Explanations

    investigations and reporting incidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bust
    -0.07
    Heat
    -0.06
    NX
    -0.06
    Financial
    -0.06
     var
    -0.06
     strip
    -0.06
    NP
    -0.06
     didSet
    -0.06
     Bast
    -0.06
    esin
    -0.06
    POSITIVE LOGITS
    elsey
    0.07
    oriasis
    0.06
     موجود
    0.06
    eline
    0.06
     Prev
    0.06
     autop
    0.06
    larınızı
    0.06
     kolej
    0.06
     milano
    0.06
     darüber
    0.06
    Act Density 0.146%

    No Known Activations