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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    birthday
    -0.07
     vant
    -0.06
    ognition
    -0.06
    參
    -0.06
    -fat
    -0.06
    [color
    -0.06
    ,n
    -0.06
    rvé
    -0.06
    Decrypt
    -0.06
    	cc
    -0.06
    POSITIVE LOGITS
    лади
    0.07
     FITNESS
    0.06
    oralType
    0.06
     Neh
    0.06
    (Activity
    0.06
    REW
    0.06
    三个
    0.06
    (Member
    0.06
     Classified
    0.06
     Choosing
    0.06
    Act Density 0.114%

    No Known Activations