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

    Neuronpedia

    INDEX
    Explanations

    wr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thổ
    -0.07
    ip
    -0.07
    一流
    -0.07
    ult
    -0.07
    esse
    -0.07
    InitialState
    -0.07
     Indicator
    -0.07
    -online
    -0.07
    .&
    -0.07
    Eu
    -0.06
    POSITIVE LOGITS
     Wr
    0.09
     wr
    0.08
     Mg
    0.08
    .getLong
    0.07
     contin
    0.07
     quir
    0.07
     Про
    0.07
     estrogen
    0.07
     ngồi
    0.07
     Wrath
    0.07
    Act Density 0.006%

    No Known Activations