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

    Neuronpedia

    INDEX
    Explanations

    daily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Messenger
    -0.07
     Layers
    -0.07
    Из
    -0.07
    listing
    -0.06
    imits
    -0.06
    _numbers
    -0.06
    阵
    -0.06
    ubyte
    -0.06
     crater
    -0.06
     Boy
    -0.06
    POSITIVE LOGITS
    acic
    0.07
    retim
    0.07
    ($('#
    0.06
     dgv
    0.06
    ého
    0.06
    .PR
    0.06
    .Tasks
    0.06
    379
    0.06
     средство
    0.06
    529
    0.06
    Act Density 0.020%

    No Known Activations