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

    Neuronpedia

    INDEX
    Explanations

    their children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اع
    0.51
    APER
    0.51
    र्सन
    0.49
    for
    0.46
    nu
    0.46
    ó
    0.45
    agers
    0.43
    APs
    0.43
    lang
    0.43
     Pipelines
    0.42
    POSITIVE LOGITS
     riport
    0.53
     diez
    0.53
     richiesta
    0.52
     prise
    0.52
     rempl
    0.50
     psic
    0.50
     huevo
    0.50
     przechowy
    0.50
     vati
    0.50
     impresionante
    0.49
    Act Density 0.000%

    No Known Activations