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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nictvím
    -0.08
     لع
    -0.07
    ουργ
    -0.06
    Không
    -0.06
     Voor
    -0.06
     Winners
    -0.06
    _Release
    -0.06
    trinsic
    -0.06
    ิหาร
    -0.06
     believable
    -0.06
    POSITIVE LOGITS
    -touch
    0.07
    241
    0.07
    onte
    0.07
    .stat
    0.07
     touch
    0.06
     心
    0.06
    ']/
    0.06
     продук
    0.06
    希
    0.06
     attributes
    0.06
    Act Density 0.000%

    No Known Activations