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

    Neuronpedia

    INDEX
    Explanations

    suggesting a better way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    穑
    -2.72
    ⍢
    -2.70
    ⽬
    -2.64
     enorme
    -2.55
    馊
    -2.48
     ſame
    -2.47
    珝
    -2.42
    ㌧
    -2.41
    ערות
    -2.36
    锖
    -2.34
    POSITIVE LOGITS
    With
    3.42
    When
    3.31
    Some
    3.19
    $
    3.14
    Although
    3.09
     However
    3.08
    While
    3.00
    That
    2.98
    Also
    2.97
    If
    2.92
    Act Density 0.019%

    No Known Activations