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

    Neuronpedia

    INDEX
    Explanations

    origins and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iteracy
    -0.91
     mainline
    -0.90
     actualmente
    -0.90
     cały
    -0.89
     again
    -0.88
     those
    -0.88
    Immediately
    -0.87
     tier
    -0.87
     my
    -0.85
     mengapa
    -0.85
    POSITIVE LOGITS
    смарт
    0.91
    當時
    0.90
     proposal
    0.89
     mwaka
    0.86
    haped
    0.85
     beginnings
    0.84
     begon
    0.82
     آینده
    0.81
     stew
    0.80
     Ciencias
    0.80
    Act Density 0.147%

    No Known Activations