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

    Neuronpedia

    INDEX
    Explanations

    the word "again" and similar sentence connectors, often with low activation for nearby words

    oai_token-act-pair · gemini-2.0-flash

    Again

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     G
    -0.48
    osha
    -0.44
    badlogic
    -0.42
    tonode
    -0.42
    UALA
    -0.42
    bka
    -0.42
    宫
    -0.42
    arashtra
    -0.41
    نم
    -0.41
     bassin
    -0.40
    POSITIVE LOGITS
     SwiftUI
    0.79
    DockStyle
    0.73
     समीक्षाओं
    0.69
     doInBackground
    0.67
    NUMX
    0.66
     IFTTT
    0.63
    MLLoader
    0.63
     actionMode
    0.61
    UpInside
    0.61
     uLocal
    0.60
    Act Density 0.929%

    No Known Activations