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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urger
    -0.07
    support
    -0.07
    ritten
    -0.07
     combines
    -0.07
    дж
    -0.06
    -upper
    -0.06
    ären
    -0.06
     Sid
    -0.06
     segunda
    -0.06
     mostr
    -0.06
    POSITIVE LOGITS
    compression
    0.06
     منابع
    0.06
     Rox
    0.06
    .fullName
    0.06
    787
    0.06
     Till
    0.06
     experimented
    0.06
    ReceiveMemoryWarning
    0.06
    Preparing
    0.06
    BinContent
    0.06
    Act Density 0.003%

    No Known Activations