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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (TIM
    -0.07
    orig
    -0.07
     HD
    -0.06
     lineback
    -0.06
     confidentiality
    -0.06
    orque
    -0.06
     Сред
    -0.06
     Royals
    -0.06
    SFML
    -0.06
    ُل
    -0.06
    POSITIVE LOGITS
    招聘
    0.07
     //----------------------------------------------------------------
    0.07
     IconData
    0.06
    |^
    0.06
    agra
    0.06
    Empresa
    0.06
    .but
    0.06
    สมาช
    0.06
    .SetValue
    0.06
     şirket
    0.06
    Act Density 0.011%

    No Known Activations