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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VICES
    -0.07
    .Disabled
    -0.07
     Virus
    -0.07
     Cavs
    -0.07
                                 ↵
    -0.07
    erras
    -0.07
     Survivor
    -0.07
    curacy
    -0.07
     Sand
    -0.07
    するのが
    -0.07
    POSITIVE LOGITS
    庑
    0.08
    を目
    0.07
    posted
    0.07
     orderby
    0.07
    Opened
    0.07
    ┍
    0.06
    oon
    0.06
    -information
    0.06
    ונים
    0.06
    橱
    0.06
    Act Density 0.002%

    No Known Activations