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

    Neuronpedia

    INDEX
    Explanations

    variable names followed by delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']],
    0.42
     terlalu
    0.38
    ();//
    0.36
     거고
    0.36
    śmy
    0.35
    ELEASE
    0.34
    mallow
    0.34
     практике
    0.34
    getitem
    0.34
     transpiration
    0.34
    POSITIVE LOGITS
    ):
    0.73
    ){
    0.70
    )
    0.64
     ):
    0.53
    _)
    0.52
     ){
    0.51
    )=>{
    0.50
    ）：
    0.50
    )?
    0.49
    ?)
    0.47
    Act Density 0.042%

    No Known Activations