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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mensaje
    -0.07
    .environment
    -0.06
     ecs
    -0.06
    lightbox
    -0.06
     libertine
    -0.06
    혼
    -0.06
    www
    -0.06
     वस
    -0.06
     rugs
    -0.06
    총
    -0.06
    POSITIVE LOGITS
    adius
    0.07
     oy
    0.06
    izia
    0.06
    amespace
    0.06
    uppe
    0.06
     itm
    0.06
     withheld
    0.06
     pwd
    0.06
     chrono
    0.06
     CT
    0.06
    Act Density 0.058%

    No Known Activations