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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    certificate
    -0.07
    เ
    -0.07
     classifier
    -0.06
    }:{
    -0.06
    ่าอ
    -0.06
    /controllers
    -0.06
    .Reg
    -0.06
    .Servlet
    -0.06
     gubern
    -0.06
    -А
    -0.06
    POSITIVE LOGITS
     جمع
    0.06
    .GetLength
    0.06
    qs
    0.06
    `,
    0.06
     많은
    0.06
     Homemade
    0.06
     hod
    0.06
     Jon
    0.06
     Option
    0.06
    ?",
    0.05
    Act Density 0.030%

    No Known Activations