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

    Neuronpedia

    INDEX
    Explanations

    new or following phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hotel
    0.95
    ওয়ে
    0.94
    Handle
    0.91
     Arbeit
    0.90
    Condition
    0.88
    Mission
    0.88
    Paf
    0.87
     Função
    0.87
    Pemb
    0.87
    mitt
    0.86
    POSITIVE LOGITS
     centroids
    0.96
    خ
    0.96
     sighs
    0.95
     victims
    0.95
    יה
    0.90
     commenc
    0.89
     lawns
    0.88
     равномер
    0.88
     probablement
    0.87
     laughs
    0.86
    Act Density 0.000%

    No Known Activations