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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENTE
    -0.06
    iese
    -0.06
    емо
    -0.06
     chấm
    -0.06
    پ
    -0.06
     reliability
    -0.06
     imposing
    -0.06
    etails
    -0.06
     motivo
    -0.06
    elly
    -0.06
    POSITIVE LOGITS
    D
    0.10
     d
    0.07
     D
    0.07
     DIN
    0.07
     몰
    0.07
     D
    0.07
    Д
    0.07
    d
    0.07
    
    0.07
    H
    0.06
    Act Density 0.001%

    No Known Activations