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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.51
    -
    0.46
    4
    0.44
    rd
    0.43
    .
    0.43
    ').
    0.42
     panels
    0.42
    ब्दिक
    0.42
     extremes
    0.42
    g
    0.41
    POSITIVE LOGITS
    íb
    0.59
     विकेट
    0.49
    InterfaceLine
    0.49
    Ẫ
    0.48
    tbLabel
    0.48
    Pergunta
    0.47
     まで
    0.46
     Saab
    0.46
     інтер
    0.45
     Неза
    0.45
    Act Density 0.001%

    No Known Activations