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

    Neuronpedia

    INDEX
    Explanations

    background information or color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     robot
    0.42
     доказа
    0.41
     convince
    0.40
     persuade
    0.40
    dule
    0.37
     have
    0.37
     opt
    0.37
    boat
    0.37
    öpf
    0.37
    的表现
    0.37
    POSITIVE LOGITS
     Background
    1.05
     background
    0.96
    background
    0.93
     BACKGROUND
    0.92
    Background
    0.91
    BACKGROUND
    0.91
     배경
    0.88
     backgrounds
    0.84
     背景
    0.82
    背景
    0.77
    Act Density 0.009%

    No Known Activations