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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auto
    -0.07
     coastline
    -0.06
    Sim
    -0.06
    liter
    -0.06
     UART
    -0.06
     emphasis
    -0.06
     люб
    -0.06
     nových
    -0.06
     prophet
    -0.06
     cáo
    -0.06
    POSITIVE LOGITS
     "../
    0.07
     gays
    0.07
     interested
    0.06
    __
    0.06
    ascript
    0.06
    NotBlank
    0.06
    _PTR
    0.06
     productId
    0.06
    _Il
    0.06
    {@
    0.06
    Act Density 0.021%

    No Known Activations