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

    Neuronpedia

    INDEX
    Explanations

    phrases and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.51
    配置
    0.49
    便
    0.49
    Asie
    0.46
     দ
    0.46
    </td>
    0.45
    :
    0.44
    Flam
    0.43
     infl
    0.43
    ,/
    0.43
    POSITIVE LOGITS
     três
    0.52
    芠
    0.50
     messa
    0.49
     luôn
    0.49
     potencial
    0.49
     présente
    0.49
    튤
    0.48
    sell
    0.48
    <0xA1>
    0.47
    𝔪
    0.47
    Act Density 0.000%

    No Known Activations