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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :
↵
    -0.06
    :
    -0.06
     reforms
    -0.06
    .registration
    -0.06
    ingo
    -0.06
    .
↵
↵
    -0.06
    Cum
    -0.06
     Yahoo
    -0.06
    Protocol
    -0.06
     odd
    -0.06
    POSITIVE LOGITS
     getArguments
    0.07
     cherche
    0.06
    Moved
    0.06
     подой
    0.06
    .PictureBoxSizeMode
    0.06
    NSE
    0.06
    .angular
    0.06
     ці
    0.06
    посеред
    0.06
    晚
    0.06
    Act Density 0.008%

    No Known Activations