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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.52
    ými
    0.49
    ல்
    0.45
     IncludeField
    0.45
    fromParams
    0.45
    öst
    0.44
     millió
    0.42
    二进制
    0.42
     пришли
    0.41
    бил
    0.41
    POSITIVE LOGITS
     behest
    0.64
     this
    0.64
    f
    0.64
     intervals
    0.64
     the
    0.60
     endroits
    0.60
     at
    0.59
    rocities
    0.59
    na
    0.58
     outset
    0.58
    Act Density 0.159%

    No Known Activations