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

    Neuronpedia

    INDEX
    Explanations

    java code, date format, regular expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кров
    0.43
     fencing
    0.42
     towers
    0.41
    Bapt
    0.40
    quipe
    0.40
     неде
    0.40
    薦
    0.39
     производ
    0.38
    Tower
    0.37
     fence
    0.37
    POSITIVE LOGITS
     simpl
    0.75
     simplification
    0.70
    simplify
    0.67
    简化
    0.65
     simplify
    0.64
     Simpl
    0.64
     simplicity
    0.64
     simplifying
    0.64
    SimpleDateFormat
    0.63
     sempl
    0.63
    Act Density 0.001%

    No Known Activations