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

    Neuronpedia

    INDEX
    Explanations

    causes unconsciousness, refers to, a designer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    コロ
    0.40
     Pop
    0.38
    proud
    0.38
     പല
    0.38
    ajes
    0.38
    Pop
    0.38
    讓人
    0.37
    fas
    0.37
    anyone
    0.37
    coordinated
    0.37
    POSITIVE LOGITS
     बाएं
    0.43
    kne
    0.42
    图像
    0.41
     nghệ
    0.40
    需要
    0.39
     अभ्यर्थ
    0.39
     dz
    0.38
     arrivare
    0.38
     планы
    0.38
    DZ
    0.38
    Act Density 0.000%

    No Known Activations