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

    Neuronpedia

    INDEX
    Explanations

    creation and designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dvs
    0.75
     sommige
    0.71
     управлять
    0.69
     các
    0.69
     procesos
    0.68
     các
    0.68
     ज्यात
    0.68
     problèmes
    0.67
     critters
    0.67
     dieren
    0.67
    POSITIVE LOGITS
     indication
    0.91
    indication
    0.91
     दर्शाता
    0.89
    represents
    0.81
    confirmation
    0.76
     precedente
    0.76
    reminder
    0.75
     reminder
    0.75
     reminiscent
    0.75
     signifies
    0.75
    Act Density 0.377%

    No Known Activations