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

    Neuronpedia

    INDEX
    Explanations

    property expenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bá
    0.41
     cier
    0.39
     colonia
    0.39
     cruciate
    0.39
     killer
    0.38
     Augmented
    0.38
     Well
    0.37
     gesture
    0.37
     äußer
    0.37
    ↪
    0.37
    POSITIVE LOGITS
    かもし
    0.40
    शिता
    0.39
    chocolate
    0.39
    Chocolate
    0.37
    som
    0.37
    wol
    0.37
    dough
    0.36
    ंगी
    0.36
     PCE
    0.35
     оно
    0.35
    Act Density 0.001%

    No Known Activations