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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azel
    -0.07
     goggles
    -0.07
    .tv
    -0.07
     eks
    -0.06
     Cousins
    -0.06
    .once
    -0.06
    แดง
    -0.06
    eger
    -0.06
    neck
    -0.06
    cents
    -0.06
    POSITIVE LOGITS
     initiated
    0.07
     города
    0.07
    是由
    0.07
    雇主
    0.07
    Using
    0.07
     Sort
    0.07
     było
    0.07
     throughout
    0.06
     experimented
    0.06
     guarda
    0.06
    Act Density 0.009%

    No Known Activations