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

    Neuronpedia

    INDEX
    Explanations

    slate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iggs
    -0.08
     волос
    -0.08
     outbound
    -0.07
    warning
    -0.07
     IHttp
    -0.07
     gór
    -0.07
    iff
    -0.07
    ሙ
    -0.07
    oute
    -0.07
    .InnerException
    -0.07
    POSITIVE LOGITS
     chem
    0.08
    自来
    0.07
    ５
    0.06
    𝐋
    0.06
    无线电
    0.06
    STREAM
    0.06
    FORM
    0.06
    ８
    0.06
    ProductName
    0.06
    ４
    0.06
    Act Density 0.001%

    No Known Activations