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

    Neuronpedia

    INDEX
    Explanations

    intensifiers for adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     весьма
    0.54
    峴
    0.51
     oldukça
    0.50
     نہایت
    0.50
     helt
    0.48
     довольно
    0.47
     매우
    0.46
    իս
    0.46
     veoma
    0.46
     بالکل
    0.46
    POSITIVE LOGITS
    多的
    0.64
    厉害
    0.61
    可怕
    0.57
     disgusting
    0.54
    敏感
    0.53
     ridiculous
    0.52
    辛苦
    0.52
    神秘
    0.51
    有趣
    0.51
    注重
    0.51
    Act Density 0.003%

    No Known Activations