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

    Neuronpedia

    INDEX
    Explanations

    index index, key key, state private

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cot
    1.16
    つまり
    1.15
    fired
    1.13
    cz
    1.04
    l
    1.03
    es
    1.02
    care
    1.02
    equivalent
    1.02
    leaf
    1.01
     sponsoring
    1.00
    POSITIVE LOGITS
    𝘿
    1.46
    ﻪ
    1.43
    ㊗
    1.42
     vorhanden
    1.37
     detract
    1.36
    ﻬ
    1.35
    рни
    1.34
    🥎
    1.34
    прочем
    1.34
     ситуа
    1.33
    Act Density 0.001%

    No Known Activations