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

    Neuronpedia

    INDEX
    Explanations

    Finding controls in UI code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    酡
    -0.07
    纯粹
    -0.07
    ÜR
    -0.07
     esc
    -0.06
    ჩ
    -0.06
    Cancel
    -0.06
     anticipation
    -0.06
     CONST
    -0.06
     pursued
    -0.06
    单纯的
    -0.06
    POSITIVE LOGITS
    就是要
    0.08
    ;"↵
    0.07
     problems
    0.07
     العلاقة
    0.07
    multip
    0.07
    �
    0.07
     Sentence
    0.07
    idable
    0.07
    LastName
    0.06
    (light
    0.06
    Act Density 0.002%

    No Known Activations