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

    Neuronpedia

    INDEX
    Explanations

    ultimately destroyed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     morf
    0.49
     intest
    0.46
     மொழி
    0.45
     intrig
    0.44
     ადამიან
    0.44
     impulse
    0.43
     registr
    0.43
     introdu
    0.42
    ាត
    0.42
     horr
    0.42
    POSITIVE LOGITS
    année
    0.44
    gå
    0.43
    pallet
    0.41
    ASON
    0.38
    setcounter
    0.38
    ACIONES
    0.37
    ামে
    0.37
    equal
    0.36
    щать
    0.36
    MJ
    0.36
    Act Density 0.002%

    No Known Activations