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

    Neuronpedia

    INDEX
    Explanations

    discriminating algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ier
    0.47
     semblance
    0.45
     pendant
    0.40
    et
    0.40
    さんが
    0.40
     portability
    0.40
     ping
    0.40
     predicament
    0.38
     battle
    0.38
     qualifying
    0.38
    POSITIVE LOGITS
     ලි
    0.50
     струк
    0.48
     estructuras
    0.48
    whether
    0.47
    maları
    0.47
    asını
    0.46
    нил
    0.45
    ត្រូ
    0.45
    tahun
    0.45
     переписи
    0.45
    Act Density 0.007%

    No Known Activations