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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frontal
    -0.10
    quiring
    -0.08
     beoordelen
    -0.08
    Requirements
    -0.08
    week
    -0.07
    Backdrop
    -0.07
     unforgettable
    -0.07
    etect
    -0.07
    Clar
    -0.07
     mide
    -0.07
    POSITIVE LOGITS
    (port
    0.08
     porta
    0.08
     Тогда
    0.08
    անձ
    0.08
     jars
    0.08
    шылар
    0.08
     cynical
    0.08
     RFC
    0.07
     Trusted
    0.07
     tournaments
    0.07
    Act Density 0.025%

    No Known Activations