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

    Neuronpedia

    INDEX
    Explanations

    dependency version declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )="
    0.40
     Howe
    0.39
     howl
    0.38
     concealment
    0.37
    olyte
    0.36
     composure
    0.36
    蜂蜜
    0.36
    <unused1059>
    0.35
     lunch
    0.35
     styl
    0.35
    POSITIVE LOGITS
    ติดตั้ง
    0.38
     especial
    0.38
     Это
    0.38
     Ministerio
    0.38
     പ്രത്യേ
    0.37
     ministerio
    0.37
    compatible
    0.37
    那是
    0.37
    兼容
    0.36
    permitAll
    0.36
    Act Density 0.009%

    No Known Activations