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

    Neuronpedia

    INDEX
    Explanations

    .animation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.37
    appelle
    0.36
    ＆
    0.35
    ovao
    0.34
     बद
    0.34
    GetComponent
    0.33
    ferd
    0.33
     tenements
    0.33
    getX
    0.33
     sätt
    0.33
    POSITIVE LOGITS
    过滤器
    0.39
     escritor
    0.38
     ഇടതു
    0.37
    不錯
    0.37
     अनुमति
    0.36
     защиту
    0.35
     보호
    0.35
    direita
    0.35
    保護
    0.35
    衣装
    0.35
    Act Density 0.009%

    No Known Activations