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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filters
    -0.07
     тут
    -0.06
     detrimental
    -0.06
     full
    -0.06
    Streamer
    -0.06
    간
    -0.06
    (Group
    -0.06
     exceedingly
    -0.06
    _successful
    -0.06
    356
    -0.06
    POSITIVE LOGITS
     regularization
    0.07
    JSImport
    0.07
    строй
    0.06
    Paginator
    0.06
    ="↵
    0.06
    punkt
    0.06
     USAGE
    0.06
     LSB
    0.06
    uciones
    0.06
     déjà
    0.06
    Act Density 0.008%

    No Known Activations