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

    Neuronpedia

    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $t
    -0.06
     Tu
    -0.06
     hour
    -0.06
    _Internal
    -0.06
     �
    -0.06
    �
    -0.06
    pink
    -0.06
     yellow
    -0.06
    Thus
    -0.06
    �
    -0.05
    POSITIVE LOGITS
     Records
    0.09
    antwort
    0.07
     records
    0.07
     record
    0.07
    rear
    0.07
     paints
    0.07
     đại
    0.06
    规模
    0.06
     ф
    0.06
     Dere
    0.06
    Act Density 0.005%

    No Known Activations