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
     languages
    -0.08
     perpetrators
    -0.07
    _arr
    -0.07
    .server
    -0.07
     kterého
    -0.06
     notre
    -0.06
     PlayStation
    -0.06
     buurt
    -0.06
     packets
    -0.06
     praising
    -0.06
    POSITIVE LOGITS
    DCALL
    0.07
     Renewable
    0.07
     retire
    0.07
    ']");↵
    0.06
     messy
    0.06
    піон
    0.06
    /"↵
    0.06
     Mixing
    0.06
    chure
    0.06
     sleepy
    0.06
    Act Density 0.083%

    No Known Activations