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

    Neuronpedia

    INDEX
    Explanations

    following `should` or `walk`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    타
    0.41
    ต
    0.39
     الف
    0.38
    фа
    0.38
    ﻤ
    0.37
    BAN
    0.37
    кта
    0.36
     picnics
    0.36
    і
    0.36
     meanings
    0.35
    POSITIVE LOGITS
     Notably
    0.42
    を用いて
    0.41
     zusätzliche
    0.39
     imparted
    0.39
     hadn
    0.39
     aead
    0.39
     کردیا
    0.38
     forze
    0.38
     laissant
    0.38
     Như
    0.36
    Act Density 0.001%

    No Known Activations