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

    Neuronpedia

    INDEX
    Explanations

    hash function and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    1.09
    ın
    1.02
    ные
    1.01
    <0xA1>
    1.00
    ियों
    0.97
    the
    0.96
    <0xBE>
    0.93
    gwood
    0.91
    х
    0.91
    ich
    0.89
    POSITIVE LOGITS
     hash
    1.28
    ל
    1.24
    ก
    1.22
     Hash
    1.21
    ות
    1.18
    Hash
    1.15
     sytu
    1.12
    ם
    1.09
     Dirección
    1.02
     belieb
    1.02
    Act Density 0.006%

    No Known Activations