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

    Neuronpedia

    INDEX
    Explanations

    html code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Metall
    1.00
     metallurgical
    0.96
     металли
    0.96
    জাত
    0.92
     Jug
    0.91
    נם
    0.90
    旁
    0.90
    ▬
    0.88
     निकाली
    0.88
     auditorium
    0.88
    POSITIVE LOGITS
     honestly
    1.23
     vuelva
    1.20
     haha
    1.16
     davvero
    1.13
    femin
    1.09
     tantas
    1.09
    Senha
    1.09
     honesty
    1.07
     terribly
    1.07
    简直
    1.06
    Act Density 0.005%

    No Known Activations