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

    Neuronpedia

    INDEX
    Explanations

    for/to followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     altre
    1.01
     annen
    1.00
    ्स
    1.00
     altri
    0.99
     hoher
    0.99
    ぞれ
    0.98
     kişiler
    0.97
     друго
    0.96
     klient
    0.94
    sächlich
    0.94
    POSITIVE LOGITS
    <0x8B>
    0.97
    н
    0.94
    ン
    0.91
    n
    0.88
    <0xB2>
    0.87
    ф
    0.87
    <0xBA>
    0.84
    th
    0.83
    sof
    0.83
    iam
    0.83
    Act Density 0.079%

    No Known Activations