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

    Neuronpedia

    INDEX
    Explanations

    taste and flavor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wolves
    1.31
    ใหญ่
    1.28
    tedir
    1.25
    န်း
    1.25
    iť
    1.24
    辶
    1.24
    ızı
    1.23
    託
    1.21
     nanoparticle
    1.20
    しも
    1.19
    POSITIVE LOGITS
    d
    1.22
     mors
    1.18
    €™
    1.11
    vamos
    1.08
    ك
    1.07
    и
    1.05
    Д
    1.05
    醂
    1.03
    <bos>
    1.02
     Dari
    0.99
    Act Density 0.078%

    No Known Activations