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

    Neuronpedia

    INDEX
    Explanations

    SQL Server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    -3.31
     Then
    -2.98
     Easily
    -2.75
    9
    -2.64
    3
    -2.64
     But
    -2.63
    1
    -2.63
    鴴
    -2.41
    Ideally
    -2.39
     ：
    -2.34
    POSITIVE LOGITS
     theres
    3.09
    鏖
    2.50
    铤
    2.47
    铩
    2.44
    ing
    2.44
    yelitis
    2.42
     to
    2.41
    渽
    2.31
    镭
    2.30
     декабря
    2.28
    Act Density 0.012%

    No Known Activations