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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _strike
    -0.07
     Gu
    -0.06
    敵
    -0.06
    WINDOW
    -0.06
     Cort
    -0.06
     turnover
    -0.06
    授
    -0.06
     rebut
    -0.06
     preocup
    -0.06
    .StObject
    -0.06
    POSITIVE LOGITS
    Humans
    0.07
     Filename
    0.07
     jub
    0.07
     born
    0.07
    份
    0.06
     října
    0.06
    HERE
    0.06
    овой
    0.06
    _CLICK
    0.06
     provoked
    0.06
    Act Density 0.072%

    No Known Activations