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

    Neuronpedia

    INDEX
    Explanations

    code delimiters or structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Datas
    0.70
    håll
    0.68
    float
    0.67
    斛
    0.67
    aS
    0.65
     UIF
    0.65
    ुकी
    0.64
    🦦
    0.64
    گی
    0.63
    ivy
    0.63
    POSITIVE LOGITS
     может
    0.93
     temat
    0.88
     Может
    0.86
     кому
    0.84
     chiều
    0.82
     चर्चित
    0.81
    ется
    0.79
     слегка
    0.79
    ɴ
    0.79
     mitä
    0.78
    Act Density 0.005%

    No Known Activations