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

    Neuronpedia

    INDEX
    Explanations

    padding and truncation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Deborah
    0.44
    UseVisualStyle
    0.41
     Deborah
    0.39
     stifle
    0.39
    Usage
    0.37
     উঠলাম
    0.37
     shelf
    0.36
    راہیم
    0.36
    şa
    0.36
     እንዳ
    0.36
    POSITIVE LOGITS
     Padding
    0.51
     padding
    0.50
    padding
    0.47
     truncation
    0.46
    Padding
    0.43
    PADDING
    0.42
     deal
    0.42
     padded
    0.39
    chop
    0.39
    deal
    0.39
    Act Density 0.005%

    No Known Activations