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

    Neuronpedia

    INDEX
    Explanations

    Zakopane, Zack Taylor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     молит
    0.95
    osome
    0.93
    ിക
    0.88
    ਠ
    0.88
     acabado
    0.84
     Pattes
    0.81
    под
    0.80
     phối
    0.79
     tỏa
    0.77
    ानगर
    0.77
    POSITIVE LOGITS
     Perché
    0.99
    rition
    0.99
    செ
    0.98
    ၠ
    0.95
    存于互联网档案馆
    0.89
     tuned
    0.88
    涉及
    0.88
    ступ
    0.86
     forgetting
    0.84
     የመ
    0.83
    Act Density 0.035%

    No Known Activations