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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伤
    -0.07
     Edwards
    -0.06
     trường
    -0.06
     LinearGradient
    -0.06
    詞
    -0.06
    励
    -0.06
     sẻ
    -0.06
    (super
    -0.06
     subprocess
    -0.06
    nga
    -0.06
    POSITIVE LOGITS
     即
    0.06
    ////////
    0.06
     laugh
    0.06
     glimps
    0.06
    _Log
    0.06
     adulte
    0.05
    PLICIT
    0.05
    �
    0.05
    ιο
    0.05
    即
    0.05
    Act Density 0.020%

    No Known Activations