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

    Neuronpedia

    INDEX
    Explanations

    ...

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     таке
    -0.07
    uers
    -0.06
     Cush
    -0.06
    enderit
    -0.06
     nă
    -0.06
    нить
    -0.06
    Border
    -0.06
    Vertex
    -0.06
     Idol
    -0.06
    ias
    -0.06
    POSITIVE LOGITS
    vote
    0.07
     migrating
    0.06
    .databinding
    0.06
     preparing
    0.06
    (rd
    0.06
    :')↵
    0.06
    Collapsed
    0.06
    elfth
    0.06
    474
    0.06
    "}↵↵
    0.06
    Act Density 0.000%

    No Known Activations