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

    Neuronpedia

    INDEX
    Explanations

    staple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lyn
    -0.07
    upt
    -0.07
     letto
    -0.07
     Ret
    -0.07
     Bett
    -0.07
    ceased
    -0.07
     visualize
    -0.06
     Ин
    -0.06
    уб
    -0.06
    泪水
    -0.06
    POSITIVE LOGITS
     Stap
    0.07
    絕對
    0.07
    鲔
    0.07
    trl
    0.07
    ⍥
    0.07
     crank
    0.07
    .total
    0.07
    _wrong
    0.07
    ping
    0.07
    _TABLE
    0.07
    Act Density 0.002%

    No Known Activations