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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VC
    -0.07
    ቱ
    -0.07
     Duffy
    -0.07
    גל
    -0.07
    ARS
    -0.07
     комф
    -0.06
     Fowler
    -0.06
    鲘
    -0.06
     Mathf
    -0.06
    쉔
    -0.06
    POSITIVE LOGITS
     timestamps
    0.08
    _TRIANGLE
    0.06
     situated
    0.06
     //{
↵
    0.06
     wzglę
    0.06
    |;↵
    0.06
     complying
    0.06
    日凌晨
    0.06
     imminent
    0.06
     untuk
    0.06
    Act Density 0.023%

    No Known Activations