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

    Neuronpedia

    INDEX
    Explanations

    Miscellaneous text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CONTROL
    -0.06
     insults
    -0.06
    AMES
    -0.06
     australia
    -0.06
     Patient
    -0.06
     Control
    -0.06
    _Input
    -0.06
    _visible
    -0.06
     insurance
    -0.06
     стала
    -0.06
    POSITIVE LOGITS
     Bộ
    0.08
    !");↵
    0.06
    есп
    0.06
    reach
    0.06
    션
    0.06
     Telecom
    0.06
    loyment
    0.06
     brightly
    0.06
    deprecated
    0.06
    ΑΝ
    0.06
    Act Density 0.000%

    No Known Activations