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

    Neuronpedia

    INDEX
    Explanations

    declaration and tag separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amsfonts
    0.43
    Counter
    0.40
    offsetWidth
    0.39
    äss
    0.38
    Infinity
    0.38
    fontawesome
    0.37
    рованию
    0.37
    asth
    0.37
    TRR
    0.37
    sympy
    0.36
    POSITIVE LOGITS
     breakup
    0.45
     splinter
    0.44
    标签
    0.43
     tags
    0.43
     declaration
    0.42
     tag
    0.41
     déclar
    0.41
     Declaration
    0.40
     burning
    0.40
     alignment
    0.39
    Act Density 0.000%

    No Known Activations