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

    Neuronpedia

    INDEX
    Explanations

    date or time stamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     will
    -1.42
     so
    -1.25
     for
    -1.07
     usually
    -0.99
     which
    -0.99
     on
    -0.98
     or
    -0.92
    !!!!!
    -0.89
     over
    -0.89
     four
    -0.87
    POSITIVE LOGITS
    プラスチック
    1.14
    もとも
    1.10
     SINCE
    1.05
    當然
    1.03
     calitate
    1.02
    Andere
    1.02
     recentemente
    1.02
     havet
    1.02
    誒
    1.01
     opérateur
    1.00
    Act Density 0.016%

    No Known Activations