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

    Neuronpedia

    INDEX
    Explanations

    skulle sedan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lade
    0.68
    ologie
    0.68
    ዥ
    0.65
     scratch
    0.64
    bane
    0.63
     extends
    0.61
    nze
    0.61
     জানে
    0.60
    opause
    0.60
     الذين
    0.60
    POSITIVE LOGITS
     olla
    1.13
     vara
    0.99
     leva
    0.92
     visa
    0.91
     ge
    0.86
     være
    0.86
     být
    0.84
     pega
    0.83
     modifica
    0.83
    Visa
    0.82
    Act Density 0.001%

    No Known Activations