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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ать
    -0.07
     Dod
    -0.07
    umor
    -0.07
    /env
    -0.07
    946
    -0.06
    _floor
    -0.06
    470
    -0.06
    ゆ
    -0.06
    Dod
    -0.06
     tapered
    -0.06
    POSITIVE LOGITS
     set
    0.07
    setParameter
    0.07
     cleared
    0.07
    лаб
    0.06
    .fill
    0.06
     seized
    0.06
    tainment
    0.06
     depressing
    0.06
     contre
    0.06
     cảnh
    0.06
    Act Density 0.009%

    No Known Activations