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

    Neuronpedia

    INDEX
    Explanations

    purpose or reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நன்கு
    0.52
    ciones
    0.50
    ágina
    0.49
    üng
    0.47
    ádiz
    0.47
    nung
    0.45
    posición
    0.45
    uede
    0.45
    របស់
    0.44
     把
    0.44
    POSITIVE LOGITS
     impro
    0.52
     iniz
    0.48
     curtains
    0.43
     thiện
    0.42
     klinik
    0.42
     ignite
    0.42
     disqualify
    0.42
    猁
    0.42
     im
    0.42
     chrom
    0.42
    Act Density 0.001%

    No Known Activations