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

    Neuronpedia

    INDEX
    Explanations

    solid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вплив
    -0.07
    -frame
    -0.06
     measurements
    -0.06
    리를
    -0.06
    ัส
    -0.06
    .flatMap
    -0.06
    avings
    -0.06
    tatus
    -0.06
     anomalies
    -0.06
     그냥
    -0.06
    POSITIVE LOGITS
    個人
    0.06
    ,:)
    0.06
    .FILL
    0.06
     也
    0.06
     aDecoder
    0.06
    .UN
    0.06
    '},
↵
    0.06
    _batches
    0.06
    >Nama
    0.06
    ',//
    0.06
    Act Density 0.005%

    No Known Activations