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

    Neuronpedia

    INDEX
    Explanations

    1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yas
    0.84
    Yas
    0.70
    ದ್
    0.69
    एट
    0.68
     पहली
    0.67
     there
    0.67
     concepts
    0.66
     AT
    0.66
     else
    0.65
    初
    0.64
    POSITIVE LOGITS
    entraî
    0.88
    лана
    0.78
     outgrowth
    0.70
     dugout
    0.69
     доро
    0.69
     caiu
    0.68
    ப்படுத்து
    0.67
     گیند
    0.67
    üyor
    0.66
     offrire
    0.65
    Act Density 0.028%

    No Known Activations