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

    Neuronpedia

    INDEX
    Explanations

    replace with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डिजाइनर
    0.74
     thêm
    0.68
    เพิ่ม
    0.68
     begin
    0.67
     jär
    0.67
     helpful
    0.67
    botao
    0.66
    关键词
    0.66
    併
    0.66
    冰箱
    0.65
    POSITIVE LOGITS
     placeholders
    1.45
     placeholder
    1.39
     replacing
    1.33
     Replace
    1.32
     replacement
    1.32
    replace
    1.31
    Replace
    1.30
     replace
    1.30
    替换
    1.27
    Placeholder
    1.26
    Act Density 0.264%

    No Known Activations