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

    Neuronpedia

    INDEX
    Explanations

    Co

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     throw
    -0.07
     строк
    -0.07
     window
    -0.07
     página
    -0.07
     terminal
    -0.07
     strange
    -0.07
    Try
    -0.07
    OUNCE
    -0.07
     pass
    -0.07
    scribers
    -0.07
    POSITIVE LOGITS
    澴
    0.08
     Coaching
    0.07
    �
    0.07
    ﯮ
    0.07
     Jamaica
    0.07
    煤
    0.07
    Co
    0.07
    反应
    0.07
     equipos
    0.07
    ☫
    0.07
    Act Density 0.104%

    No Known Activations