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

    Neuronpedia

    INDEX
    Explanations

    are there any specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onu
    0.78
     만들어
    0.78
    それが
    0.77
    ものが
    0.76
     இணைந்து
    0.75
     успешно
    0.74
     bunu
    0.73
     يق
    0.73
    問題を
    0.73
     trovano
    0.72
    POSITIVE LOGITS
     there
    1.35
    there
    1.08
     ther
    0.99
     देयर
    0.91
     their
    0.90
     هناك
    0.90
     any
    0.89
    ther
    0.88
     There
    0.81
     certain
    0.80
    Act Density 0.059%

    No Known Activations