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

    Neuronpedia

    INDEX
    Explanations

    float or caption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ServiceName
    0.43
     Nhân
    0.42
     Brick
    0.39
     Applications
    0.38
     Hidden
    0.37
     ক্রিয়া
    0.37
    Brick
    0.37
    igi
    0.36
    LetterIndex
    0.36
    ComponentName
    0.36
    POSITIVE LOGITS
     floats
    0.88
     float
    0.87
     floating
    0.85
     floated
    0.84
    float
    0.81
    Floating
    0.79
     Float
    0.78
    浮
    0.78
    Float
    0.77
     Floating
    0.76
    Act Density 0.003%

    No Known Activations