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

    Neuronpedia

    INDEX
    Explanations

    years ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /-}$
    1.05
    在
    1.05
     deserial
    1.01
    ventud
    0.98
     двери
    0.95
    ка
    0.94
    etera
    0.94
    ुसार
    0.94
    ्ह
    0.92
     ensue
    0.92
    POSITIVE LOGITS
    وں
    0.78
     वर
    0.77
    ningen
    0.77
    ак
    0.77
    ний
    0.76
    ének
    0.75
    لي
    0.75
     ago
    0.74
    нды
    0.74
     ventilated
    0.74
    Act Density 0.149%

    No Known Activations