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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    periences
    -0.07
     kits
    -0.07
     Deb
    -0.07
    uent
    -0.07
     websocket
    -0.06
     Legacy
    -0.06
     Does
    -0.06
     Span
    -0.06
     Друг
    -0.06
    itlement
    -0.06
    POSITIVE LOGITS
     �
    0.06
     TIME
    0.06
    �
    0.06
     PLL
    0.05
    Break
    0.05
     일을
    0.05
    044
    0.05
     chăm
    0.05
    ısıt
    0.05
    WithIdentifier
    0.05
    Act Density 0.011%

    No Known Activations