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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (utf
    -0.07
     slack
    -0.07
    _ADV
    -0.07
     hơn
    -0.07
    侵占
    -0.07
     terrace
    -0.07
     CONST
    -0.06
    Ȁ
    -0.06
     생
    -0.06
    _tC
    -0.06
    POSITIVE LOGITS
    慶
    0.08
     familiarity
    0.07
    副教授
    0.07
    ICON
    0.07
    ActionButton
    0.07
    校长
    0.07
    採
    0.07
     jacket
    0.07
    洽谈
    0.07
    节
    0.07
    Act Density 0.001%

    No Known Activations